INDEX

Explanations

words related to listening or attention

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Janeiro

-0.65

 Palm

-0.63

eros

-0.63

mber

-0.63

rament

-0.62

INAL

-0.61

\/\/

-0.60

 Leap

-0.59

esan

-0.58

 redemption

-0.58

POSITIVE LOGITS

 attent

1.34

 listened

0.94

 aloud

0.92

 closely

0.92

 listens

0.91

 passively

0.88

 listen

0.85

 listening

0.85

 loudly

0.83

 patiently

0.83

Activations Density 0.017%

words related to listening or attention

No Comments

No Known Activations