© 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. 0-RES-JB
    11. 4141
    Prev
    Next
    INDEX
    Explanations

    words related to disinfection and cleanliness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to water disinfection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGS
    -0.81
    ATS
    -0.74
     Apart
    -0.71
    naires
    -0.70
     Indians
    -0.67
    esa
    -0.67
    Apart
    -0.66
    ickets
    -0.66
    elope
    -0.66
    IPS
    -0.65
    POSITIVE LOGITS
     subsequ
    0.74
     lamp
    0.69
     lever
    0.67
     portrayed
    0.66
     thumb
    0.66
     wielded
    0.65
     repr
    0.64
     portrayal
    0.63
     nost
    0.63
     charact
    0.63
    Activations Density 0.000%

    No Known Activations