INDEX

Explanations

phrases related to instructions or steps

oai_token-act-pair · gpt-3.5-turbo

empty or placeholder content in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ä»£

-0.61

apo

-0.56

Guest

-0.55

raq

-0.54

 Moroc

-0.54

é¾

-0.53

itud

-0.53

aughed

-0.53

ipal

-0.52

itol

-0.52

POSITIVE LOGITS

 guys

0.80

're

0.76

RS

0.76

hei

0.73

 dont

0.69

 wanna

0.68

 Choose

0.65

kai

0.64

've

0.62

your

0.61

Activations Density 0.200%

phrases related to instructions or steps

empty or placeholder content in the text

No Comments

No Known Activations