INDEX

Explanations

references to or mentions of "dimension"

oai_token-act-pair · gpt-3.5-turbo

references to various dimensions

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

ublic

-0.76

doms

-0.75

oaded

-0.70

yright

-0.70

rero

-0.69

cific

-0.68

otle

-0.66

INST

-0.66

EA

-0.66

giving

-0.66

POSITIVE LOGITS

 dimension

0.97

dimension

0.94

imensional

0.94

 dimensions

0.93

 dimensional

0.89

ality

0.78

 Nept

0.78

dimensional

0.76

 Dimension

0.72

 Dimensions

0.72

Activations Density 0.019%

references to or mentions of "dimension"

references to various dimensions

No Comments

No Known Activations