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. 13296
    Prev
    Next
    INDEX
    Explanations

    image captions with names of photographers or photo agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to images and photo credits associated with a publication

    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
    uca
    -0.90
    stood
    -0.74
     Spice
    -0.73
    bye
    -0.73
    theless
    -0.68
    rough
    -0.68
    mong
    -0.66
    hap
    -0.65
    gae
    -0.64
    aido
    -0.64
    POSITIVE LOGITS
    ################################
    0.93
     Caption
    0.80
    actionDate
    0.75
     [|
    0.72
    Loading
    0.70
    thumbnails
    0.69
    âĶĢâĶĢâĶĢâĶĢ
    0.68
     srfAttach
    0.66
    Loader
    0.65
    },"
    0.65
    Activations Density 0.043%

    No Known Activations