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. 4-RES-JB
    6. 17582
    Prev
    Next
    INDEX
    Explanations

    phrases indicating affiliation or association with organizations or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of affiliations or associations with entities or groups

    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
    aqu
    -0.71
    pter
    -0.69
    chat
    -0.69
    oufl
    -0.64
    Detailed
    -0.64
    pecting
    -0.63
    confidence
    -0.63
    bra
    -0.62
    pan
    -0.62
    =-=-=-=-=-=-=-=-
    -0.61
    POSITIVE LOGITS
     affili
    1.15
     affiliated
    1.15
    hips
    1.08
    iliated
    1.04
     affiliation
    1.00
    lia
    0.93
     affiliate
    0.88
    affiliated
    0.79
     affiliates
    0.77
    iance
    0.76
    Activations Density 0.014%

    No Known Activations