INDEX

Explanations

phrases referring to components or elements within a system

oai_token-act-pair · gpt-3.5-turbo

terms related to components and 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

paces

-0.91

ettings

-0.90

cape

-0.81

anders

-0.80

pace

-0.78

cale

-0.75

poons

-0.73

ilver

-0.71

scl

-0.71

venants

-0.70

POSITIVE LOGITS

iously

0.83

ality

0.83

less

0.79

ment

0.75

ry

0.74

ially

0.73

iety

0.73

uated

0.72

enary

0.72

 adjunct

0.71

Activations Density 0.062%

phrases referring to components or elements within a system

terms related to components and elements in various contexts

No Comments

No Known Activations