© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10205
    Prev
    Next
    INDEX
    Explanations

    references to file directories or paths

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that are formatted as metadata or elements in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grimes
    -0.65
     tender
    -0.64
    emouth
    -0.63
     Tasman
    -0.62
     unsus
    -0.62
     infiltr
    -0.62
     Moody
    -0.61
     inqu
    -0.60
     intimid
    -0.59
     Illinois
    -0.59
    POSITIVE LOGITS
    pmwiki
    1.15
    ËĪ
    1.09
    Getty
    0.98
    Flickr
    0.96
    etc
    0.96
    usr
    0.95
    articles
    0.91
    photos
    0.89
    docs
    0.86
    legal
    0.85
    Activations Density 0.057%

    No Known Activations