© 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. 10-RES-JB
    11. 21444
    Prev
    Next
    INDEX
    Explanations

    proper nouns and brand names in sentences

    oai_token-act-pair · gpt-3.5-turbo

    subjects related to societal and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.66
    ces
    -0.64
    CI
    -0.62
    poses
    -0.62
    started
    -0.59
    didn
    -0.59
    said
    -0.58
    externalActionCode
    -0.57
    was
    -0.57
    ross
    -0.56
    POSITIVE LOGITS
     survive
    1.25
     prove
    1.21
     succeed
    1.20
     be
    1.20
     prevail
    1.14
     become
    1.13
     convince
    1.11
     suffice
    1.10
     deprive
    1.08
     inspire
    1.07
    Activations Density 0.159%

    No Known Activations