INDEX

Explanations

dates or time-related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "start" and related terminology

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

 entirety

-0.66

 majority

-0.65

æ©Ł

-0.61

illard

-0.61

 keyboards

-0.60

 surv

-0.60

selves

-0.60

 compan

-0.60

 bearer

-0.59

 Bastard

-0.59

POSITIVE LOGITS

nings

1.27

ribune

0.92

ups

0.86

ners

0.84

up

0.80

date

0.78

UP

0.77

othal

0.77

strap

0.76

points

0.75

Activations Density 0.047%

dates or time-related terms

occurrences of the word "start" and related terminology

No Comments

No Known Activations