INDEX

Explanations

the word "or" in various contexts

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

ires

-0.79

estern

-0.78

erest

-0.77

rue

-0.76

olicy

-0.75

irms

-0.74

axies

-0.72

-0.71

estro

-0.69

arten

-0.69

POSITIVE LOGITS

chard

0.98

 alternatively

0.97

ifice

0.93

acles

0.89

 equival

0.88

acle

0.83

chest

0.82

chid

0.82

acular

0.81

phans

0.79

Activations Density 0.039%

the word "or" in various contexts

No Comments

No Known Activations