© 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. 7-RES-JB
    11. 13403
    Prev
    Next
    INDEX
    Explanations

    text related to various problems or issues

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "problems" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orks
    -0.69
    sheet
    -0.64
    iversary
    -0.63
    ographies
    -0.63
    rib
    -0.63
    rica
    -0.63
    ron
    -0.61
    tip
    -0.61
    Asia
    -0.60
    alty
    -0.60
    POSITIVE LOGITS
    hooting
    1.28
     plag
    1.18
    hift
    0.90
     stemming
    0.88
     arise
    0.88
     affecting
    0.87
     arising
    0.84
    olving
    0.83
     relating
    0.81
    afe
    0.79
    Activations Density 0.063%

    No Known Activations