INDEX

Explanations

phrases related to error messages

oai_token-act-pair · gpt-3.5-turbo

references to errors and error handling

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

electric

-0.87

tsky

-0.81

Electric

-0.79

apy

-0.76

jen

-0.75

airo

-0.70

apeake

-0.68

ILA

-0.68

nai

-0.67

rolet

-0.67

POSITIVE LOGITS

ously

0.92

 margin

0.89

uracy

0.85

prone

0.85

 prone

0.82

fully

0.79

hooting

0.79

gered

0.77

 correction

0.75

 correcting

0.75

Activations Density 0.039%

phrases related to error messages

references to errors and error handling

No Comments

No Known Activations