INDEX

Explanations

phrases or clauses indicating a hypothetical scenario or unreal situation

oai_token-act-pair · gpt-3.5-turbo

conditional phrases

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

eph

-0.68

omen

-0.67

Offline

-0.67

hess

-0.65

highest

-0.65

phrine

-0.65

verts

-0.64

aukee

-0.64

arest

-0.64

LINE

-0.64

POSITIVE LOGITS

yip

0.87

 indul

0.69

acan

0.69

 they

0.68

 nothing

0.66

lication

0.64

 knowingly

0.62

 menacing

0.62

 somebody

0.61

 amalg

0.60

Activations Density 0.014%

phrases or clauses indicating a hypothetical scenario or unreal situation

conditional phrases

No Comments

No Known Activations