© 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. 22627
    Prev
    Next
    INDEX
    Explanations

    words related to job titles and positions, such as 'Sergeant', 'Boss', and 'Doctor'

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or characters

    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
    tumblr
    -0.72
     mascot
    -0.71
    ||||
    -0.69
    Untitled
    -0.69
     ..........
    -0.67
     AAA
    -0.65
     infring
    -0.65
    prototype
    -0.64
     tram
    -0.64
     Marketable
    -0.63
    POSITIVE LOGITS
    aney
    0.83
    eger
    0.79
    hner
    0.77
     said
    0.77
    arkin
    0.77
    inen
    0.75
    anson
    0.74
     explained
    0.73
    evin
    0.73
    ynski
    0.73
    Activations Density 0.249%

    No Known Activations