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. 5-RES-JB
    6. 12245
    Prev
    Next
    INDEX
    Explanations

    invitations or events that involve participation or attendance

    oai_token-act-pair · gpt-3.5-turbo

    references to invitations or events that involve participation or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥ¬
    -0.79
    Ħ¢
    -0.76
    dress
    -0.68
     separating
    -0.67
    grass
    -0.67
    ¥µ
    -0.65
     cleaner
    -0.65
     horizontally
    -0.64
    ©¶æ
    -0.63
    bian
    -0.63
    POSITIVE LOGITS
    itations
    1.36
    incible
    1.31
    itational
    1.30
    asion
    1.26
    igor
    1.22
    itation
    1.19
    ulnerable
    1.17
    asions
    1.15
    olve
    1.13
    olved
    1.12
    Activations Density 0.011%

    No Known Activations