INDEX

Explanations

specific characters or symbols in the text

oai_token-act-pair · gpt-3.5-turbo

the end-of-text token

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 explan

-0.93

 agre

-0.90

chnology

-0.83

 ende

-0.83

 behavi

-0.82

ngth

-0.80

 obser

-0.79

 horizont

-0.76

 viability

-0.75

 independ

-0.75

POSITIVE LOGITS

é¾į

0.93

ef

0.91

ãĤ±

0.87

Â°

0.82

irect

0.82

ļ

0.82

Âº

0.82

Ĭ

0.80

¤

0.80

Counter

0.79

Activations Density 0.041%

specific characters or symbols in the text

the end-of-text token

No Comments

No Known Activations