INDEX

Explanations

references to teachers and educators

oai_token-act-pair · gpt-3.5-turbo

references to teachers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

rils

-0.88

tera

-0.74

ril

-0.74

axy

-0.65

hawks

-0.65

rencies

-0.64

 launchers

-0.63

00200000

-0.62

obin

-0.62

ulence

-0.62

POSITIVE LOGITS

girls

0.92

 Teachers

0.88

 Teacher

0.85

heet

0.82

 teacher

0.81

children

0.78

achers

0.75

student

0.75

girl

0.75

 teachers

0.74

Activations Density 0.028%

references to teachers and educators

references to teachers

No Comments

No Known Activations