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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 15342
    Prev
    Next
    INDEX
    Explanations

    phrases related to information technology and connectivity

    oai_token-act-pair · gpt-3.5-turbo

    prepositions or indications of purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.74
    brance
    -0.66
    imbabwe
    -0.64
    asonry
    -0.63
    Offline
    -0.62
    edience
    -0.61
     duty
    -0.61
     lapse
    -0.59
     withdrawals
    -0.59
    EFF
    -0.58
    POSITIVE LOGITS
    osate
    0.72
     Qin
    0.70
    anus
    0.69
    vable
    0.67
    aird
    0.65
    yout
    0.65
    gettable
    0.65
    PLA
    0.65
    tan
    0.64
    å¥
    0.63
    Activations Density 0.000%

    No Known Activations