© 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. 10-RES-JB
    11. 6976
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "difficult" followed by the word "for"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express difficulty or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    querque
    -0.83
    claimed
    -0.74
    ngth
    -0.73
     teasp
    -0.73
    hazard
    -0.70
    ashtra
    -0.70
    jab
    -0.68
    DAQ
    -0.68
    ersed
    -0.68
    Interstitial
    -0.66
    POSITIVE LOGITS
     us
    1.30
     anyone
    1.20
     me
    1.18
     someone
    1.16
     anybody
    1.11
     them
    1.11
     him
    1.10
     outsiders
    1.03
     somebody
    1.03
     people
    1.02
    Activations Density 0.109%

    No Known Activations