INDEX

Explanations

questions or speech markers

oai_token-act-pair · gpt-3.5-turbo

empty text sections or content with minimal keywords

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

 airports

-0.66

CPS

-0.62

odcast

-0.57

 similarly

-0.57

 industries

-0.56

 occasion

-0.56

 climates

-0.55

CPI

-0.55

 reprint

-0.55

 resulting

-0.54

POSITIVE LOGITS

Brother

0.85

Daddy

0.84

Dad

0.82

bye

0.80

soever

0.76

Yo

0.73

 nomine

0.73

 Daddy

0.73

.""

0.71

Father

0.71

Activations Density 0.189%

questions or speech markers

empty text sections or content with minimal keywords

No Comments

No Known Activations