© 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. 22525
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical proximity and direction

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to emotional connections and interactions

    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
     distinction
    -0.64
     specificity
    -0.61
    oria
    -0.58
     rapport
    -0.58
    PN
    -0.57
     PID
    -0.57
     commissioners
    -0.57
     obser
    -0.55
    iness
    -0.55
     XX
    -0.54
    POSITIVE LOGITS
    aneously
    1.19
    rely
    0.86
    edly
    0.86
    etheless
    0.84
    without
    0.82
    til
    0.82
     throughout
    0.81
     onto
    0.77
    ilaterally
    0.77
     alike
    0.76
    Activations Density 0.392%

    No Known Activations