© 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. 20685
    Prev
    Next
    INDEX
    Explanations

    information or discussions related to rumors and social gossip

    oai_token-act-pair · gpt-3.5-turbo

    references to gossip and tabloid culture

    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
    arcity
    -0.87
    mega
    -0.84
    asio
    -0.83
    uman
    -0.81
    avored
    -0.77
    annis
    -0.77
    emp
    -0.76
    inence
    -0.73
    anamo
    -0.73
    oral
    -0.73
    POSITIVE LOGITS
     gossip
    1.09
     Leilan
    0.79
    pool
    0.77
    abilia
    0.77
     columnist
    0.76
     rumours
    0.75
     banter
    0.74
    ãĥ¼ãĥĨãĤ£
    0.74
     rumors
    0.74
    dale
    0.73
    Activations Density 0.008%

    No Known Activations