© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 18738
    Prev
    Next
    INDEX
    Explanations

    words related to physical contact or combat, such as "hug" or "attack."

    oai_token-act-pair · gpt-3.5-turbo

    political statements and references to geopolitical relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realised
    -0.71
     realise
    -0.70
     favourites
    -0.61
     recognise
    -0.59
     organise
    -0.58
     devs
    -0.58
     apologise
    -0.58
     organising
    -0.56
     whilst
    -0.56
    isation
    -0.56
    POSITIVE LOGITS
     ALEC
    0.63
     Libertarian
    0.62
     Southwest
    0.61
     statewide
    0.61
     nonprofit
    0.61
     nonpartisan
    0.60
     taxpayer
    0.60
     congressional
    0.60
     nonprofits
    0.59
     bipartisan
    0.59
    Activations Density 2.457%

    No Known Activations