INDEX

Explanations

terms related to trees

oai_token-act-pair · gpt-3.5-turbo

mentions of trees

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Goth

-0.79

REDACTED

-0.69

ISO

-0.69

 Parenthood

-0.68

OK

-0.66

 Tonight

-0.66

 Hitman

-0.66

 Jenner

-0.62

enegger

-0.62

 Dragonbound

-0.61

POSITIVE LOGITS

bled

1.18

bling

1.11

asured

1.10

pe

1.07

bles

1.04

ble

1.02

pees

0.97

anium

0.97

bors

0.96

gement

0.96

Activations Density 0.005%

terms related to trees

mentions of trees

No Comments

No Known Activations