© 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. 6-RES-JB
    11. 8512
    Prev
    Next
    INDEX
    Explanations

    keywords related to the impact or effect of events on various aspects of life or society

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the effects and impacts of various actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Forbidden
    -0.71
     Sins
    -0.65
     Begin
    -0.65
     Dong
    -0.63
     Bom
    -0.61
     pitches
    -0.61
     Bugs
    -0.60
     Alps
    -0.59
     Fatal
    -0.59
    Fail
    -0.58
    POSITIVE LOGITS
     reverber
    0.95
     impacting
    0.90
     affecting
    0.89
     impact
    0.87
     negatively
    0.86
     effect
    0.85
    notation
    0.84
     multiplier
    0.83
     impacts
    0.82
     adversely
    0.81
    Activations Density 0.060%

    No Known Activations