© 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. 4297
    Prev
    Next
    INDEX
    Explanations

    exaggerated descriptions or claims

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exaggeration

    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
    spot
    -0.75
    aining
    -0.72
    NetMessage
    -0.70
    IU
    -0.69
    Assembly
    -0.67
    abiding
    -0.65
    fighters
    -0.64
    ¯¯¯¯¯¯¯¯
    -0.64
    phabet
    -0.64
    */(
    -0.64
    POSITIVE LOGITS
     exagger
    1.31
     exaggeration
    1.12
     exaggerated
    1.05
     overest
    0.88
     inflated
    0.82
    200000
    0.80
     misunder
    0.79
     distortions
    0.77
     modesty
    0.76
     unbeliev
    0.72
    Activations Density 0.015%

    No Known Activations