© 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. 6511
    Prev
    Next
    INDEX
    Explanations

    phrases related to statements of intent or action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong opinions or significant actions related to leadership or events

    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
    vere
    -0.68
    ach
    -0.65
     [+
    -0.63
    Grey
    -0.62
    grades
    -0.62
    auder
    -0.56
     Vish
    -0.55
    urable
    -0.54
     Die
    -0.53
    ofer
    -0.53
    POSITIVE LOGITS
     immediately
    0.97
     instantly
    0.85
     promptly
    0.84
    mediately
    0.79
     greeted
    0.79
    uddenly
    0.75
     astonished
    0.74
     assumed
    0.74
     faced
    0.73
     flo
    0.73
    Activations Density 0.280%

    No Known Activations