Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 20077
    Prev
    Next
    INDEX
    Explanations

    questions starting with "What makes" and "What distinguishes" and discusses differences or qualities that set things apart from others

    oai_token-act-pair · gpt-3.5-turbo

    questions that seek to understand the defining qualities or characteristics of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.86
    erenn
    -0.73
    abad
    -0.73
    ixel
    -0.71
    EEE
    -0.68
    estern
    -0.68
    rentice
    -0.67
    bill
    -0.67
    pard
    -0.66
    lex
    -0.66
    POSITIVE LOGITS
     Sanct
    0.76
     distinguishes
    0.71
    pires
    0.70
     motiv
    0.68
     Fit
    0.66
     Cu
    0.65
     ISIL
    0.64
     Klu
    0.64
    orno
    0.64
     motivating
    0.63
    Activations Density 0.087%

    No Known Activations