© 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. 11581
    Prev
    Next
    INDEX
    Explanations

    words related to military units or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to battalions or military groups

    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
    ãĥĩãĤ£
    -0.98
    çīĪ
    -0.80
    ãĤ´ãĥ³
    -0.77
    IELD
    -0.74
    ãĥĵ
    -0.73
    ãĤ·ãĥ£
    -0.72
    çĶ°
    -0.70
    ãĥĨãĤ£
    -0.70
     Âł Âł Âł Âł
    -0.68
    20439
    -0.67
    POSITIVE LOGITS
    alions
    0.95
    ued
    0.83
    igators
    0.79
    uing
    0.79
    endix
    0.77
    pload
    0.76
    aukee
    0.75
    cffff
    0.75
    leground
    0.74
    oths
    0.74
    Activations Density 0.051%

    No Known Activations