INDEX

Explanations

texts with specific formatting quirks

oai_token-act-pair · gpt-3.5-turbo

conversational prompts or questions about experiences and opinions

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

conom

-0.65

acan

-0.62

 lifes

-0.61

 Tinder

-0.60

 Uran

-0.59

 gunned

-0.57

 upstairs

-0.57

 fleeing

-0.57

 crosses

-0.57

uno

-0.57

POSITIVE LOGITS

Answer

1.07

YES

0.77

OVA

0.75

Yes

0.75

Correct

0.74

Interview

0.73

Yeah

0.72

RM

0.72

gow

0.71

ÂłÂłÂłÂłÂłÂłÂłÂł

0.71

Activations Density 0.105%

texts with specific formatting quirks

conversational prompts or questions about experiences and opinions

No Comments

No Known Activations