INDEX

Explanations

words related to "graphic" representations or descriptions, particularly in science or technology 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

ndra

-0.91

eer

-0.72

eers

-0.71

 Nuggets

-0.70

FUL

-0.64

pee

-0.63

eva

-0.59

creen

-0.58

nect

-0.58

 fitting

-0.57

POSITIVE LOGITS

ysics

1.24

obia

1.24

obic

1.19

ysical

1.11

osph

1.02

ract

0.95

atform

0.93

otics

0.92

ying

0.90

agos

0.90

Activations Density 0.003%

words related to "graphic" representations or descriptions, particularly in science or technology contexts

No Comments

No Known Activations