© 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. 24088
    Prev
    Next
    INDEX
    Explanations

    words related to technical components and measurements, such as transistors and gigabytes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant concepts, structures, or phenomena

    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
     RH
    -0.63
     EB
    -0.60
     MU
    -0.59
     CB
    -0.58
     CR
    -0.56
     SC
    -0.55
    wal
    -0.54
     CM
    -0.54
     KR
    -0.53
     AB
    -0.53
    POSITIVE LOGITS
    terday
    0.82
    tml
    0.81
    hower
    0.75
    heses
    0.73
    phabet
    0.72
    forcement
    0.72
    apy
    0.70
    agram
    0.70
    recy
    0.70
    andr
    0.70
    Activations Density 0.235%

    No Known Activations