© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 710
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns denoting people or roles

    oai_token-act-pair · gpt-4-turbo

    mentions of people and their relationships in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or professional qualifications and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surface
    -0.53
    ologies
    -0.47
     Coverage
    -0.46
    Mech
    -0.45
     Requires
    -0.45
    othermal
    -0.43
     Surface
    -0.43
     Mages
    -0.42
     substrate
    -0.42
    prev
    -0.41
    POSITIVE LOGITS
    iazep
    0.58
     wife
    0.53
     girlfriend
    0.52
     secretary
    0.51
    wife
    0.51
     grandson
    0.50
    代
    0.50
     mentor
    0.50
    vik
    0.47
     honorary
    0.47
    Activations Density 5.140%

    No Known Activations