© 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. 2-RES-JB
    11. 1918
    Prev
    Next
    INDEX
    Explanations

    phrases related to the human body, particularly focusing on the abdomen and hips

    oai_token-act-pair · gpt-3.5-turbo

    terms related to injuries or anatomical references to the abdomen and torso

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ggies
    -0.91
    channelAvailability
    -0.74
    mberg
    -0.73
    ãģ¦
    -0.72
    zing
    -0.70
     Flavoring
    -0.70
    displayText
    -0.69
    ãģ®éŃĶ
    -0.68
    HCR
    -0.68
     Jobs
    -0.67
    POSITIVE LOGITS
     torso
    0.99
     abdomen
    0.99
     circumference
    0.91
    ysis
    0.86
     cavity
    0.84
    mast
    0.84
     thighs
    0.84
     thigh
    0.83
     lobe
    0.82
    estinal
    0.81
    Activations Density 0.009%

    No Known Activations