INDEX

Explanations

statements indicating blame or responsibility

oai_token-act-pair · gpt-3.5-turbo

references to personal responsibility or blame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

atform

-0.81

atos

-0.81

CHO

-0.80

ISTER

-0.80

iolet

-0.78

¥µ

-0.75

chin

-0.74

thia

-0.74

å¥³

-0.74

apist

-0.73

POSITIVE LOGITS

lessly

1.05

 forgiven

0.86

 fault

0.83

 Fault

0.81

 faults

0.80

lessness

0.77

ously

0.76

less

0.71

 Karma

0.68

line

0.68

Activations Density 0.019%

statements indicating blame or responsibility

references to personal responsibility or blame

No Comments

No Known Activations