INDEX

Explanations

phrases related to a central point or focal point

oai_token-act-pair · gpt-3.5-turbo

terms related to key points or central themes

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

odcast

-0.78

 inhibitors

-0.68

 assimil

-0.66

ubi

-0.66

cham

-0.65

yson

-0.65

ippery

-0.64

 millenn

-0.64

utics

-0.63

atson

-0.62

POSITIVE LOGITS

 focal

0.86

eral

0.84

ãĤ¤ãĥĪ

0.82

pha

0.82

rament

0.78

imation

0.78

point

0.78

ãĥĥãĤ¯

0.78

stones

0.76

 point

0.76

Activations Density 0.036%

phrases related to a central point or focal point

terms related to key points or central themes

No Comments

No Known Activations