INDEX

Explanations

the word "Carson"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Carson."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 glac

-0.78

yk

-0.75

*/(

-0.75

lihood

-0.74

hops

-0.70

ebin

-0.66

dayName

-0.66

 streng

-0.66

 Header

-0.65

 newsp

-0.65

POSITIVE LOGITS

 Daly

0.97

 Carson

0.96

 Went

0.93

 Palmer

0.92

illo

0.83

isma

0.83

usk

0.82

ota

0.79

stown

0.77

anan

0.77

Activations Density 0.030%

the word "Carson"

mentions of the name "Carson."

No Comments

No Known Activations