© 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. 4-RES-JB
    11. 15351
    Prev
    Next
    INDEX
    Explanations

    phrases about methods, processes, or strategies

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about processes and methods

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

    No Comments

    Negative Logits
    gur
    -0.64
    ãĥ¼ãĥ³
    -0.63
    agar
    -0.63
     Evening
    -0.62
    inence
    -0.60
    rene
    -0.60
    åij
    -0.59
    iya
    -0.59
    enery
    -0.59
    feat
    -0.58
    POSITIVE LOGITS
    soever
    0.72
     relevance
    0.67
     situational
    0.66
     reconcil
    0.63
     humans
    0.61
     critically
    0.61
     algorith
    0.60
     contingency
    0.59
     sorts
    0.59
     competence
    0.59
    Activations Density 0.145%

    No Known Activations