INDEX

Explanations

information about various products or events which are being featured or highlighted

oai_token-act-pair · gpt-3.5-turbo

phrases that describe specific content or elements in various contexts

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

sis

-0.93

utral

-0.75

alty

-0.75

externalActionCode

-0.72

gee

-0.71

berman

-0.71

vernment

-0.70

cel

-0.70

apy

-0.69

si

-0.68

POSITIVE LOGITS

 prominently

1.33

Feature

0.87

 features

0.81

ttes

0.76

ãĤ¼ãĤ¦ãĤ¹

0.75

 clips

0.74

features

0.73

 Include

0.72

Featured

0.69

Features

0.69

Activations Density 0.042%

information about various products or events which are being featured or highlighted

phrases that describe specific content or elements in various contexts

No Comments

No Known Activations