INDEX

Explanations

phrases related to specific names or terms, particularly "Thompson" with varying levels of relevance

oai_token-act-pair · gpt-3.5-turbo

references to the name "Thompson."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

rator

-0.88

utive

-0.86

atories

-0.85

arial

-0.79

rators

-0.79

mble

-0.78

eas

-0.76

mate

-0.75

ations

-0.73

ter

-0.73

POSITIVE LOGITS

 Gunn

0.81

 Reuters

0.79

 Browne

0.74

sonian

0.70

stown

0.66

Yor

0.66

Rank

0.64

ACK

0.62

OGR

0.62

 Ammo

0.61

Activations Density 0.069%

phrases related to specific names or terms, particularly "Thompson" with varying levels of relevance

references to the name "Thompson."

No Comments

No Known Activations