INDEX

Explanations

phrases signaling concern or emphasis

oai_token-act-pair · gpt-3.5-turbo

phrases related to concern or awareness

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

obal

-0.71

rang

-0.69

omas

-0.67

oru

-0.65

 VIEW

-0.60

inous

-0.56

 Mahjong

-0.55

 cozy

-0.55

 Together

-0.55

iltr

-0.54

POSITIVE LOGITS

IAS

0.67

ieth

0.64

UME

0.63

.,

0.59

orsche

0.58

enth

0.58

umes

0.56

 Pole

0.56

enery

0.55

Activations Density 0.054%

phrases signaling concern or emphasis

phrases related to concern or awareness

No Comments

No Known Activations