© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6790
    Prev
    Next
    INDEX
    Explanations

    words related to military ranks and operations

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate a connection to various types of categories or classifications

    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
     Tanz
    -0.68
    ortium
    -0.67
    ests
    -0.67
     DMV
    -0.66
    tumblr
    -0.65
    ided
    -0.63
     Bieber
    -0.63
    odder
    -0.63
    killing
    -0.62
    iants
    -0.62
    POSITIVE LOGITS
     gland
    0.83
     glands
    0.75
    ksh
    0.73
    ature
    0.66
    ary
    0.65
    aries
    0.65
    ansas
    0.64
     detach
    0.64
    ussia
    0.64
    clair
    0.64
    Activations Density 0.015%

    No Known Activations