© 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. 6193
    Prev
    Next
    INDEX
    Explanations

    verbal forms denoting persistent and negative situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ongoing problems or challenges

    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
    ettel
    -0.67
    reme
    -0.67
    verts
    -0.65
    raviolet
    -0.65
    erence
    -0.64
    itar
    -0.63
    ighters
    -0.62
    uber
    -0.60
    arij
    -0.60
    endi
    -0.59
    POSITIVE LOGITS
     plagued
    1.06
     havoc
    1.02
     plag
    1.01
    luster
    0.84
    gling
    0.72
    tenance
    0.72
     dogged
    0.70
    byss
    0.70
    lehem
    0.69
     Ples
    0.69
    Activations Density 0.042%

    No Known Activations