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. 4686
    Prev
    Next
    INDEX
    Explanations

    references to sizes

    oai_token-act-pair · gpt-3.5-turbo

    references to medium sizes in various contexts

    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
     Merch
    -0.78
    çīĪ
    -0.75
    atche
    -0.72
    IGHTS
    -0.72
     Masquerade
    -0.71
    èĥ
    -0.70
    apons
    -0.69
    ä½ľ
    -0.68
    alog
    -0.68
    ADRA
    -0.67
    POSITIVE LOGITS
     sized
    1.12
    weights
    1.00
    medium
    0.89
    weight
    0.86
    ship
    0.82
     medium
    0.77
    ature
    0.76
    intendent
    0.74
    haired
    0.74
    -,
    0.71
    Activations Density 0.015%

    No Known Activations