© 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. 2-RES-JB
    11. 23103
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "Ver"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ver" or close variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.80
    ħĭ
    -0.79
    utics
    -0.73
    atform
    -0.67
    OPLE
    -0.65
    è£ħ
    -0.65
     silence
    -0.65
    ĩ
    -0.65
    NetMessage
    -0.64
    ENDED
    -0.64
    POSITIVE LOGITS
    Ver
    1.13
    dict
    1.03
    bal
    0.97
     Ver
    0.96
    bum
    0.94
    ver
    0.94
    onica
    0.90
    tex
    0.90
    million
    0.84
    rington
    0.84
    Activations Density 0.007%

    No Known Activations