INDEX

Explanations

informative snippets or excerpts from longer pieces of text

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce lists or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aneers

-0.90

alties

-0.86

©¶æ¥µ

-0.81

xit

-0.77

¨

-0.73

ãĥĺ

-0.70

culosis

-0.70

aith

-0.70

aeda

-0.69

 Parenthood

-0.69

POSITIVE LOGITS

 excerpt

0.88

 overview

0.86

 preliminary

0.83

 tentative

0.81

 partial

0.80

 provisional

0.79

 link

0.77

 rundown

0.77

 illustration

0.77

 handy

0.77

Activations Density 0.123%

informative snippets or excerpts from longer pieces of text

phrases that introduce lists or examples

No Comments

No Known Activations