© 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. 22696
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Deputy."

    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
     Pose
    -0.94
    enegger
    -0.93
    è¯
    -0.76
     Cage
    -0.74
    çĦ
    -0.73
    çķ
    -0.70
     Centauri
    -0.67
     Hole
    -0.67
    éŃĶ
    -0.65
     Akin
    -0.65
    POSITIVE LOGITS
    recated
    1.36
    uty
    1.26
    artments
    1.23
    uties
    1.19
    leted
    1.19
    arted
    1.17
    artment
    1.14
    osit
    1.09
    ressed
    1.09
    iction
    1.06
    Activations Density 0.023%

    No Known Activations