INDEX

Explanations

the word "Hunt"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Hunt."

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

Downloadha

-0.73

 Leilan

-0.70

 Seym

-0.70

 instr

-0.70

optional

-0.69

 mathemat

-0.68

sembly

-0.66

umbn

-0.65

afort

-0.64

BuyableInstoreAndOnline

-0.64

POSITIVE LOGITS

 Hunt

1.07

ley

0.99

ress

0.96

hunt

0.94

resses

0.93

leigh

0.85

cheon

0.84

Hunt

0.79

 hunts

0.78

mage

0.78

Activations Density 0.015%

the word "Hunt"

references to the name "Hunt."

No Comments

No Known Activations