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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21273
    Prev
    Next
    INDEX
    Explanations

    generic nouns with determiners and possessive pronouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "the,” indicating a strong focus on specific subjects or topics mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icia
    -0.95
    thood
    -0.76
    abetes
    -0.72
    onica
    -0.71
    Ò
    -0.70
    NB
    -0.69
    orate
    -0.68
    itored
    -0.67
    Serv
    -0.67
    bg
    -0.67
    POSITIVE LOGITS
     majority
    1.27
     slightest
    1.19
    oret
    1.12
     entire
    1.08
     vast
    1.08
     latter
    1.05
     biggest
    0.99
     easiest
    0.95
     discrepancy
    0.94
     entirety
    0.94
    Activations Density 0.457%

    No Known Activations