INDEX

Explanations

instances of the word "talk" and its variations, indicating discussions or conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

emale

-0.76

boa

-0.68

iverpool

-0.66

arte

-0.65

ritional

-0.65

eele

-0.64

orius

-0.64

zyk

-0.63

rypt

-0.62

hews

-0.61

POSITIVE LOGITS

 about

0.97

 smack

0.79

 louder

0.79

about

0.79

 aloud

0.78

 frankly

0.77

ebus

0.75

 loudly

0.75

 ABOUT

0.73

ative

0.72

Activations Density 0.031%

instances of the word "talk" and its variations, indicating discussions or conversations

No Comments

No Known Activations