© 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. 19487
    Prev
    Next
    INDEX
    Explanations

    mentions of old things, whether entities, concepts, or ideas

    oai_token-act-pair · gpt-3.5-turbo

    references to things that are "old."

    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
    utterstock
    -0.86
     athlet
    -0.83
    rawdownloadcloneembedreportprint
    -0.82
    phasis
    -0.80
    ONSORED
    -0.79
    orney
    -0.78
    illation
    -0.76
    aminer
    -0.75
    annabin
    -0.74
    Ĥİ
    -0.73
    POSITIVE LOGITS
     fashioned
    1.21
    rums
    0.91
     old
    0.85
    old
    0.79
    est
    0.79
     timers
    0.75
     standby
    0.74
     lady
    0.72
     acquaintance
    0.72
     stale
    0.72
    Activations Density 0.026%

    No Known Activations