INDEX

Explanations

problematic situations or issues

oai_token-act-pair · gpt-3.5-turbo

statements or questions about problems

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Congratulations

-0.78

throp

-0.75

 ceremony

-0.74

 vict

-0.73

gian

-0.73

 congr

-0.72

daq

-0.72

eval

-0.71

riel

-0.70

leans

-0.69

POSITIVE LOGITS

 compounded

0.83

 plag

0.82

 exacerbated

0.79

 worsened

0.78

 lack

0.78

 endemic

0.77

 inconsistency

0.77

 duplication

0.75

 faulty

0.75

 preventing

0.74

Activations Density 0.335%

problematic situations or issues

statements or questions about problems

No Comments

No Known Activations