INDEX

Explanations

locations where events are happening

oai_token-act-pair · gpt-3.5-turbo

locations and places mentioned in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

thood

-0.71

blance

-0.70

cale

-0.65

xit

-0.63

ussian

-0.63

hemy

-0.63

htaking

-0.62

haar

-0.61

 Pair

-0.61

etting

-0.60

POSITIVE LOGITS

 itself

0.94

 precinct

0.86

 floor

0.86

 perimeter

0.84

 premises

0.83

 plaza

0.82

 gates

0.81

wright

0.80

 grounds

0.78

 facility

0.78

Activations Density 0.277%

locations where events are happening

locations and places mentioned in the text

No Comments

No Known Activations