© 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. 1-RES-JB
    11. 8536
    Prev
    Next
    INDEX
    Explanations

    names or terms related to certain individuals or titles containing "hart"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "hart" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URI
    -0.75
     deaf
    -0.68
     simul
    -0.67
     sarc
    -0.65
     vit
    -0.65
    raviolet
    -0.65
     brightest
    -0.64
     recess
    -0.64
     sclerosis
    -0.64
    ntil
    -0.63
    POSITIVE LOGITS
    hart
    1.53
    ford
    1.08
    enstein
    1.06
    bone
    0.94
    hardt
    0.93
    ilton
    0.89
    awi
    0.86
    mann
    0.86
    hurst
    0.85
    meier
    0.85
    Activations Density 0.007%

    No Known Activations