© 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. 3861
    Prev
    Next
    INDEX
    Explanations

    keywords related to social issues, particularly homelessness, prostitution, and obesity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues, specifically homelessness, prostitution, and obesity

    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
    individual
    -0.64
    gran
    -0.63
     CFR
    -0.63
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.63
    Interstitial
    -0.63
    parts
    -0.63
    states
    -0.60
    TAIN
    -0.60
    Organ
    -0.59
    Lear
    -0.58
    POSITIVE LOGITS
    yip
    1.10
    anship
    0.89
     prevention
    0.82
     fuelled
    0.73
     stemming
    0.72
     challeng
    0.72
    NZ
    0.71
     arose
    0.71
    ophobia
    0.70
    thood
    0.70
    Activations Density 0.043%

    No Known Activations