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. 3-RES-JB
    6. 1310
    Prev
    Next
    INDEX
    Explanations

    words related to tension or exertion

    oai_token-act-pair · gpt-3.5-turbo

    verbs and their variations related to actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jinn
    -0.88
     avail
    -0.67
     overdue
    -0.61
     Gardens
    -0.61
     corpus
    -0.61
    enium
    -0.58
     mull
    -0.56
     sugg
    -0.56
    å¹
    -0.55
     trumpet
    -0.55
    POSITIVE LOGITS
    ngth
    0.80
    Alias
    0.71
    ggle
    0.68
    Dest
    0.67
    Connector
    0.66
    inav
    0.66
    arius
    0.66
    ainer
    0.65
    Goal
    0.65
    glers
    0.64
    Activations Density 0.112%

    No Known Activations