© 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. 9842
    Prev
    Next
    INDEX
    Explanations

    correlations between different variables or factors

    oai_token-act-pair · gpt-3.5-turbo

    correlations between behaviors and health outcomes

    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
    DragonMagazine
    -1.07
    }}}
    -0.81
    Revolution
    -0.80
    ãĤ£
    -0.80
    Think
    -0.79
    nels
    -0.78
    Laughs
    -0.78
    Phone
    -0.77
    Plug
    -0.76
    ãĥķãĤ©
    -0.75
    POSITIVE LOGITS
     susceptibility
    1.24
     obesity
    1.17
     mortality
    1.16
     coronary
    1.13
     longevity
    1.12
     cardiovascular
    1.12
     depressive
    1.09
     cognition
    1.08
     socioeconomic
    1.07
     risk
    1.07
    Activations Density 0.210%

    No Known Activations