INDEX

Explanations

phrases related to the United States and its standing in the world

oai_token-act-pair · gpt-3.5-turbo

the phrase "the US" or related references to the United States

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

 Telesc

-0.80

rouse

-0.76

ees

-0.66

ossom

-0.65

idian

-0.64

ises

-0.62

racuse

-0.61

izable

-0.61

Footnote

-0.60

ousy

-0.60

POSITIVE LOGITS

 always

0.98

 definitely

0.98

 notoriously

0.95

 certainly

0.95

 indeed

0.92

 currently

0.91

 obsessed

0.89

senal

0.88

 often

0.87

 still

0.86

Activations Density 0.543%

phrases related to the United States and its standing in the world

the phrase "the US" or related references to the United States

No Comments

No Known Activations