© 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. 5104
    Prev
    Next
    INDEX
    Explanations

    words related to providing evidence for or against a statement or claim

    oai_token-act-pair · gpt-3.5-turbo

    terms related to validating, disproving, or substantiating claims

    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
    ebus
    -0.80
    NetMessage
    -0.77
    iew
    -0.69
    aned
    -0.67
    artney
    -0.67
    oppy
    -0.67
    atra
    -0.65
    azard
    -0.65
    obbies
    -0.64
    ixtape
    -0.64
    POSITIVE LOGITS
     corrobor
    1.18
     substant
    1.12
     dispro
    1.10
     debunked
    1.03
     hypotheses
    1.01
     refute
    0.99
     debunk
    0.99
     assertions
    0.95
     evidence
    0.94
     unfounded
    0.90
    Activations Density 0.101%

    No Known Activations