INDEX

Explanations

instances where something is outside a specific location or boundary

oai_token-act-pair · gpt-3.5-turbo

prepositions indicating location or direction

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

Cola

-0.73

iasco

-0.69

NESS

-0.69

ï¸ı

-0.68

avorite

-0.66

erity

-0.66

},"

-0.65

Reviewer

-0.65

/(

-0.65

Bal

-0.64

POSITIVE LOGITS

stretched

0.68

ciating

0.65

agers

0.63

Pis

0.62

 cigarettes

0.62

 snipp

0.62

airo

0.61

ĸļ

0.59

aday

0.59

ADS

0.59

Activations Density 0.170%

instances where something is outside a specific location or boundary

prepositions indicating location or direction

No Comments

No Known Activations