© 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. 7-RES-JB
    11. 10028
    Prev
    Next
    INDEX
    Explanations

    phrases related to getting to know people, places, or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases about getting to know people or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blaming
    -0.82
    pec
    -0.73
     estimating
    -0.68
     claiming
    -0.68
     calculates
    -0.67
     mandate
    -0.67
     refusing
    -0.67
     assumption
    -0.65
    elfare
    -0.64
     Explan
    -0.64
    POSITIVE LOGITS
     firsthand
    1.48
    abilia
    0.88
     greatness
    0.85
    agine
    0.78
     scenery
    0.76
     majesty
    0.75
     whats
    0.73
    Adventure
    0.72
     glimps
    0.70
     awe
    0.68
    Activations Density 0.401%

    No Known Activations