© 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. 14817
    Prev
    Next
    INDEX
    Explanations

    terms related to software packages and commands in a Unix-like operating system

    oai_token-act-pair · gpt-3.5-turbo

    words related to aptitude and proficiency

    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
     Zimbabwe
    -0.70
     Pall
    -0.69
    EEE
    -0.69
    RFC
    -0.69
    plementation
    -0.68
    Ô
    -0.66
    izont
    -0.66
     Sheep
    -0.65
    FORE
    -0.65
     OWN
    -0.64
    POSITIVE LOGITS
    itude
    1.61
    itudes
    1.32
     apt
    0.90
    entimes
    0.87
    eus
    0.86
    itud
    0.86
    lest
    0.85
    uries
    0.79
    entious
    0.78
    urous
    0.76
    Activations Density 0.006%

    No Known Activations