© 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. 7-RES-JB
    11. 16776
    Prev
    Next
    INDEX
    Explanations

    phrases related to past behavior or performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a history or track record of actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ando
    -0.75
    agers
    -0.72
    hap
    -0.70
    tein
    -0.69
    ulp
    -0.68
    Stars
    -0.68
    ateurs
    -0.67
    ishers
    -0.67
    ople
    -0.66
    elsen
    -0.66
    POSITIVE LOGITS
     documented
    0.79
     dealings
    0.77
    acqu
    0.74
     proven
    0.69
     revolving
    0.69
     histories
    0.68
     reliability
    0.67
     abuser
    0.67
     conflicts
    0.67
     penchant
    0.67
    Activations Density 0.080%

    No Known Activations