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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 20210
    Prev
    Next
    INDEX
    Explanations

    phrases related to content or lack of content in written material

    oai_token-act-pair · gpt-3.5-turbo

    instances of absence or nonexistence related to various subjects

    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
    iffe
    -0.79
     ASA
    -0.77
     Sabha
    -0.68
    ickr
    -0.67
     Janeiro
    -0.67
    onga
    -0.67
    heit
    -0.66
    lease
    -0.65
     Recomm
    -0.65
    INESS
    -0.65
    POSITIVE LOGITS
     filler
    0.73
     prominently
    0.68
     signature
    0.68
     bumper
    0.67
     neatly
    0.65
     tantal
    0.63
    ographic
    0.63
    rians
    0.63
    ographical
    0.63
     elements
    0.62
    Activations Density 0.370%

    No Known Activations