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. 20667
    Prev
    Next
    INDEX
    Explanations

    phrases or statements presented by a specific person

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual in a context of discussion or reporting

    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
    reach
    -0.76
    noon
    -0.74
    anking
    -0.68
    iries
    -0.66
    Interested
    -0.65
    rocket
    -0.63
    Lim
    -0.63
    earch
    -0.63
    requisite
    -0.60
     expiration
    -0.58
    POSITIVE LOGITS
    'd
    1.06
    'll
    0.94
     said
    0.87
    aeus
    0.86
     wrote
    0.84
     tweeted
    0.82
    said
    0.78
     says
    0.76
     joked
    0.76
     lamented
    0.73
    Activations Density 0.079%

    No Known Activations