INDEX

Explanations

references to specific locations or events, particularly related to social or political issues

oai_token-act-pair · gpt-3.5-turbo

references to the location of Charlottesville and related events

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

berman

-0.84

pring

-0.75

matic

-0.74

STDOUT

-0.74

phant

-0.74

vana

-0.73

flix

-0.70

VIS

-0.69

tin

-0.68

graded

-0.66

POSITIVE LOGITS

ottesville

0.99

sburg

0.92

enburg

0.81

quished

0.77

 Township

0.77

 Heights

0.75

halla

0.75

 County

0.70

acre

0.69

cade

0.66

Activations Density 0.009%

references to specific locations or events, particularly related to social or political issues

references to the location of Charlottesville and related events

No Comments

No Known Activations