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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 6607
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations, assessments, analyses, or investigations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of reviews related to policies or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hots
    -0.70
    Corn
    -0.68
    pox
    -0.68
    âĹ¼
    -0.67
    pots
    -0.65
    ITIES
    -0.64
    icz
    -0.63
    onne
    -0.63
    Beaut
    -0.62
    kt
    -0.62
    POSITIVE LOGITS
    opian
    0.97
     process
    0.93
     judgment
    0.80
    spective
    0.79
     judgement
    0.79
     backlog
    0.77
     hearings
    0.75
    rador
    0.73
    essee
    0.72
     undertaken
    0.72
    Activations Density 0.026%

    No Known Activations