© 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. 9-RES-JB
    11. 18563
    Prev
    Next
    INDEX
    Explanations

    references to remains or remnants of objects or organisms

    oai_token-act-pair · gpt-3.5-turbo

    references to archaeological discoveries or remains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Availability
    -0.81
    yout
    -0.81
    IPS
    -0.80
    alert
    -0.76
    amazon
    -0.73
    zai
    -0.73
    æ©Ł
    -0.73
    oking
    -0.72
    ealous
    -0.72
    Ô
    -0.72
    POSITIVE LOGITS
     deceased
    1.25
     extinct
    1.09
     slain
    1.03
     defunct
    1.01
     aborted
    0.99
     fallen
    0.96
     civilisation
    0.89
     burial
    0.89
     murdered
    0.87
     ancient
    0.84
    Activations Density 0.240%

    No Known Activations