INDEX

Explanations

phrases related to errors or issues

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "error" and its variations

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

electric

-0.84

tsky

-0.79

apeake

-0.78

amen

-0.77

apy

-0.76

atos

-0.75

edom

-0.74

nai

-0.74

Electric

-0.74

arov

-0.69

POSITIVE LOGITS

ously

0.87

uracy

0.85

 margin

0.85

gered

0.79

 guiActiveUn

0.77

 error

0.72

 prone

0.72

fully

0.72

 deceive

0.71

 mishand

0.71

Activations Density 0.028%

phrases related to errors or issues

occurrences of the word "error" and its variations

No Comments

No Known Activations