INDEX

Explanations

technical terms related to tasks or operations

oai_token-act-pair · gpt-3.5-turbo

specific terms related to metrics and performance indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

untled

-0.80

imately

-0.74

Pg

-0.73

ollo

-0.72

putable

-0.68

andestine

-0.63

hetically

-0.62

felt

-0.62

vell

-0.62

querade

-0.61

POSITIVE LOGITS

 alike

0.70

aments

0.63

naire

0.61

£ı

0.61

(.

0.60

 gimmick

0.59

 Buddhism

0.58

"}],"

0.58

estate

0.57

©¶æ

0.56

Activations Density 0.714%

technical terms related to tasks or operations

specific terms related to metrics and performance indicators

No Comments

No Known Activations