© 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. 3-RES-JB
    11. 14079
    Prev
    Next
    INDEX
    Explanations

    the name "Guido" with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Guido"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REE
    -0.79
     Asheville
    -0.74
    rals
    -0.69
     Atmospheric
    -0.69
    ardless
    -0.69
    lees
    -0.67
     ILCS
    -0.65
    д
    -0.64
    birth
    -0.64
     Canadians
    -0.63
    POSITIVE LOGITS
    ido
    0.90
    estro
    0.90
    odo
    0.86
    utsche
    0.84
    jit
    0.83
    ctor
    0.81
    atri
    0.79
    zilla
    0.77
    emonium
    0.75
    roid
    0.75
    Activations Density 0.007%

    No Known Activations