INDEX

Explanations

adjectives with a negative connotation

oai_token-act-pair · gpt-3.5-turbo

instances of the prefix "fl" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

RAL

-0.80

HCR

-0.75

terday

-0.70

selves

-0.70

 Territory

-0.64

 annex

-0.63

 thumbs

-0.59

EMENT

-0.55

Geo

-0.55

cules

-0.55

POSITIVE LOGITS

ickr

1.30

imsy

1.27

irting

1.18

oyd

1.17

ushing

1.17

atter

1.15

utter

1.12

orescent

1.11

aky

1.09

usher

1.08

Activations Density 0.015%

adjectives with a negative connotation

instances of the prefix "fl" in various contexts

No Comments

No Known Activations