INDEX

Explanations

words related to sending or moving something back

oai_token-act-pair · gpt-3.5-turbo

instances of the word "back" and its various contexts and usages within the text

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

inational

-0.72

ision

-0.72

enaries

-0.69

ities

-0.65

izo

-0.64

entric

-0.63

ifix

-0.62

viz

-0.60

eria

-0.60

urable

-0.60

POSITIVE LOGITS

dated

1.14

GROUND

1.09

packs

1.01

wards

1.00

fired

0.96

)=(

0.95

packing

0.95

fires

0.95

haul

0.94

stab

0.93

Activations Density 0.059%

words related to sending or moving something back

instances of the word "back" and its various contexts and usages within the text

No Comments

No Known Activations