© 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. 11-RES-JB
    11. 16296
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly surrounding news events

    oai_token-act-pair · gpt-3.5-turbo

    references to survivors of traumatic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nar
    -0.84
    tun
    -0.81
    tty
    -0.76
     constitu
    -0.76
     autos
    -0.75
     na
    -0.75
     kb
    -0.75
     autop
    -0.74
     Koz
    -0.73
    AUT
    -0.72
    POSITIVE LOGITS
     Rose
    2.57
    Rose
    2.35
     Roses
    1.83
     roses
    1.66
    rose
    1.48
     rose
    1.37
     Rosen
    1.13
     Rosa
    1.06
     Thorn
    1.01
    Ros
    0.99
    Activations Density 0.235%

    No Known Activations