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. 8-RES-JB
    6. 21202
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions involving a sense of determination or courage

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "br" which likely indicates a line break or a new paragraph

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    locked
    -0.67
    EVA
    -0.66
    requires
    -0.66
    heid
    -0.65
     Decay
    -0.64
    fare
    -0.64
    chnology
    -0.63
    ŃĶ
    -0.63
    wolves
    -0.63
    POSITIVE LOGITS
    imming
    1.10
    acing
    1.00
    cms
    0.93
    ighter
    0.92
    aced
    0.91
    idal
    0.91
    indle
    0.91
    idget
    0.90
    ights
    0.89
    istle
    0.89
    Activations Density 0.018%

    No Known Activations