© 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. 18570
    Prev
    Next
    INDEX
    Explanations

    words related to outdated or old-fashioned concepts or items

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with inadequacy and obsolescence

    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
     DRAG
    -0.65
     Agents
    -0.65
     gently
    -0.64
     initials
    -0.63
    auri
    -0.61
     daddy
    -0.59
    stones
    -0.59
     foam
    -0.58
     mast
    -0.58
     watt
    -0.58
    POSITIVE LOGITS
    acy
    1.19
    ities
    1.16
    iencies
    1.13
    ately
    1.06
    ated
    1.06
    uably
    1.06
    etry
    1.04
    eties
    1.04
    adoes
    1.03
    umbered
    1.03
    Activations Density 0.079%

    No Known Activations