© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 797
    Prev
    Next
    INDEX
    Explanations

    words implying concern or unease, such as "troubling" or "worrisome"

    oai_token-act-pair · gpt-4-turbo

    words related to negative evaluations or causing distress

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating distressing or alarming situations

    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
    á
    -0.86
    tein
    -0.84
    cellence
    -0.83
    ighth
    -0.83
    oping
    -0.77
    arat
    -0.76
    ©¶æ
    -0.76
    ersion
    -0.75
    ula
    -0.75
    haw
    -0.75
    POSITIVE LOGITS
     Seas
    0.88
     worrisome
    0.81
     Earthqu
    0.81
    ly
    0.80
     newsp
    0.77
    LY
    0.74
     Concern
    0.74
     proble
    0.73
    Trend
    0.73
     Tanz
    0.72
    Activations Density 0.014%

    No Known Activations