INDEX

Explanations

references to specific names or terms, potentially related to a particular context or topic

oai_token-act-pair · gpt-3.5-turbo

the names and references associated with specific individuals and objects

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

bang

-0.78

elsen

-0.75

nce

-0.74

Interstitial

-0.65

slave

-0.65

olution

-0.64

rity

-0.64

ates

-0.63

roid

-0.62

buck

-0.62

POSITIVE LOGITS

oaded

0.92

endium

0.86

Osw

0.82

comings

0.75

Thumbnail

0.73

————

0.64

Ú

0.64

oad

0.63

leans

0.63

unct

0.63

Activations Density 0.045%

references to specific names or terms, potentially related to a particular context or topic

the names and references associated with specific individuals and objects

No Comments

No Known Activations