© 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. 11-RES-JB
    11. 6999
    Prev
    Next
    INDEX
    Explanations

    words related to music albums and releases

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to music and entertainment releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aples
    -0.66
     unanim
    -0.64
     oneself
    -0.63
    "]=>
    -0.62
    someone
    -0.62
    arching
    -0.57
    encers
    -0.56
    umbnails
    -0.56
     ransom
    -0.56
     breeze
    -0.55
    POSITIVE LOGITS
    ,,
    0.97
     Dying
    0.85
     Splash
    0.85
    é¾įåĸļ士
    0.84
     Dreams
    0.84
     Nightmares
    0.83
     Rampage
    0.81
     Silent
    0.81
     Twisted
    0.81
     Destination
    0.79
    Activations Density 0.289%

    No Known Activations