© 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. 6068
    Prev
    Next
    INDEX
    Explanations

    words containing the substring 'x'

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'x' in various contexts

    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
     Pru
    -0.83
    DERR
    -0.78
    assetsadobe
    -0.77
     convol
    -0.69
     stru
    -0.68
    sburgh
    -0.67
     exha
    -0.67
     behavi
    -0.67
    hari
    -0.66
    milo
    -0.66
    POSITIVE LOGITS
    posed
    1.15
    imity
    1.10
    actly
    1.06
    posure
    1.05
    odus
    1.03
    avier
    1.02
    press
    0.99
    posing
    0.99
    aminer
    0.95
    cellence
    0.94
    Activations Density 0.022%

    No Known Activations