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. 21118
    Prev
    Next
    INDEX
    Explanations

    references to Original Equipment Manufacturers (OEM)

    oai_token-act-pair · gpt-3.5-turbo

    references to original equipment manufacturers (OEMs) and related technological components

    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
    notations
    -0.77
    atom
    -0.77
    flies
    -0.75
    tenance
    -0.75
    hower
    -0.74
    bird
    -0.73
    stage
    -0.73
    film
    -0.72
    hot
    -0.70
    bolt
    -0.69
    POSITIVE LOGITS
    UE
    0.93
    MC
    0.92
    s
    0.89
    FP
    0.87
    UGE
    0.83
    GY
    0.83
    Vs
    0.82
    OOL
    0.81
    BIL
    0.81
    QB
    0.80
    Activations Density 0.049%

    No Known Activations