INDEX

Explanations

actionable items or tasks indicated by "*" symbols with associated importance level

oai_token-act-pair · gpt-3.5-turbo

repeated symbols or characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rolet

-0.94

eness

-0.89

ichick

-0.80

romeda

-0.79

adelphia

-0.79

ilogy

-0.75

idays

-0.74

liness

-0.73

ilitarian

-0.71

omorphic

-0.70

POSITIVE LOGITS

âĢ¢âĢ¢

1.00

âĢ¢âĢ¢âĢ¢âĢ¢

0.90

laughs

0.85

SK

0.82

COMPLE

0.81

TON

0.80

AUT

0.80

blank

0.79

ERROR

0.78

Insert

0.78

Activations Density 0.009%

actionable items or tasks indicated by "*" symbols with associated importance level

repeated symbols or characters in the text

No Comments

No Known Activations