INDEX

Explanations

names or terms related to individuals

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or entities

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

-+-+

-0.82

ï¸ı

-0.76

 Adin

-0.69

Emb

-0.67

REF

-0.66

catentry

-0.66

RET

-0.64

Legend

-0.62

 Skydragon

-0.61

 Drift

-0.61

POSITIVE LOGITS

hof

0.95

opol

0.81

ocent

0.78

iae

0.78

utical

0.75

anchester

0.74

igans

0.74

acht

0.73

nikov

0.72

ican

0.72

Activations Density 0.065%

names or terms related to individuals

mentions of specific names or entities

No Comments

No Known Activations