© 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. 5016
    Prev
    Next
    INDEX
    Explanations

    information related to people meeting each other and forming connections, primarily through introductions by third parties or online research

    oai_token-act-pair · gpt-3.5-turbo

    connections and interactions between individuals

    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
    ardless
    -0.97
    verages
    -0.81
    includes
    -0.81
    ailable
    -0.80
     encompasses
    -0.79
    except
    -0.77
     unless
    -0.77
    ersed
    -0.75
    ramid
    -0.75
    urated
    -0.75
    POSITIVE LOGITS
     overheard
    0.96
     classmate
    0.89
     acquaintance
    0.84
     classmates
    0.78
     informant
    0.78
     acquaintances
    0.76
     aunt
    0.75
     gossip
    0.74
     birthday
    0.73
     kins
    0.73
    Activations Density 0.683%

    No Known Activations