© 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. 15324
    Prev
    Next
    INDEX
    Explanations

    words related to specific food items, particularly meat cuts like 'brisket' and 'turkey'

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of meat, particularly buffalo and turkey

    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
    amin
    -0.82
    marks
    -0.75
    liga
    -0.71
    orio
    -0.70
    ugal
    -0.70
    amo
    -0.69
    Sensor
    -0.68
    affer
    -0.68
    ancing
    -0.68
    opes
    -0.68
    POSITIVE LOGITS
     brisk
    0.83
    ãģĦ
    0.75
     turkey
    0.69
    ļéĨĴ
    0.69
    DragonMagazine
    0.69
    eteria
    0.68
     trade
    0.67
     buffalo
    0.66
    ãĥ¼ãĤ¯
    0.64
     outwe
    0.64
    Activations Density 0.024%

    No Known Activations