© 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. 4-RES-JB
    11. 9260
    Prev
    Next
    INDEX
    Explanations

    verbs indicating granting, giving, or bestowing things upon others

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bestowal and the conferral of rights or honors

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

    No Comments

    Negative Logits
    inson
    -0.82
    Barn
    -0.68
    fork
    -0.65
    OPER
    -0.63
    STER
    -0.61
    Cole
    -0.61
    Ark
    -0.60
    Constructed
    -0.59
     Petersen
    -0.59
    SON
    -0.59
    POSITIVE LOGITS
    reet
    0.89
     conferred
    0.84
     Carbuncle
    0.81
    dinand
    0.81
    ghai
    0.80
    ree
    0.80
    ially
    0.79
    redients
    0.79
     bestowed
    0.79
    ennial
    0.78
    Activations Density 0.027%

    No Known Activations