INDEX

Explanations

relatively negative descriptions of people or events

oai_token-act-pair · gpt-3.5-turbo

references to the term "some," often in a dismissive or generalizing context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

enance

-0.70

ettes

-0.68

gon

-0.68

 Cycling

-0.65

tainment

-0.65

 Rouse

-0.65

SPONSORED

-0.64

 borne

-0.63

uckle

-0.61

inson

-0.61

POSITIVE LOGITS

place

1.25

ones

1.17

body

1.08

how

0.96

 semblance

0.94

 sort

0.85

 unspecified

0.83

ONE

0.82

¬¼

0.82

 obscure

0.77

Activations Density 0.104%

relatively negative descriptions of people or events

references to the term "some," often in a dismissive or generalizing context

No Comments

No Known Activations