Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21799
    Prev
    Next
    INDEX
    Explanations

    phrases related to struggle or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to struggle or difficulty in maintaining control or composure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ometimes
    -0.65
    probably
    -0.65
    rongh
    -0.63
     MAY
    -0.63
    RON
    -0.62
    asionally
    -0.61
    moil
    -0.60
    iol
    -0.59
    imus
    -0.55
     doubtless
    -0.55
    POSITIVE LOGITS
     anymore
    1.33
     adequately
    1.02
     coherent
    1.02
    enough
    0.98
     nor
    0.90
     properly
    0.89
     anything
    0.89
     adequate
    0.82
     sufficiently
    0.79
    urate
    0.76
    Activations Density 0.422%

    No Known Activations