© 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. 8-RES-JB
    11. 18490
    Prev
    Next
    INDEX
    Explanations

    phrases related to enduring challenges or situations

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    FactoryReloaded
    -0.87
    ivals
    -0.85
    ADRA
    -0.79
    ovie
    -0.78
    ITNESS
    -0.77
    wcsstore
    -0.75
    ONSORED
    -0.75
    illard
    -0.73
    reply
    -0.72
    Reward
    -0.70
    POSITIVE LOGITS
     furious
    0.97
     bothered
    0.89
     loud
    0.89
     mighty
    0.88
     spacious
    0.84
     concise
    0.83
     sustained
    0.83
     thirsty
    0.82
     dense
    0.82
     Furious
    0.81
    Activations Density 0.177%

    No Known Activations