© 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. 1-RES-JB
    11. 9468
    Prev
    Next
    INDEX
    Explanations

    dialogue quoted speech

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charm
    -0.71
     charms
    -0.70
     abandoning
    -0.67
     slapping
    -0.66
     favor
    -0.66
     bending
    -0.66
     vain
    -0.65
     imagination
    -0.65
     schedule
    -0.65
     neglect
    -0.64
    POSITIVE LOGITS
    Freedom
    0.91
    We
    0.89
    CDC
    0.84
    Ax
    0.81
    I
    0.80
    Reward
    0.80
    Never
    0.80
    Companies
    0.80
    Ku
    0.78
    Je
    0.78
    Activations Density 0.207%

    No Known Activations