INDEX

Explanations

references to "Hasbro" in the text

oai_token-act-pair · gpt-3.5-turbo

references to the brand "Hasbro."

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

 Gins

-0.68

orious

-0.66

Prim

-0.64

 Noon

-0.61

 Dull

-0.60

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.60

Nir

-0.59

 famed

-0.58

aries

-0.58

 outfield

-0.58

POSITIVE LOGITS

ccoli

1.20

bro

1.11

idered

1.00

keye

0.94

afort

0.92

vity

0.91

kes

0.91

cffff

0.90

kef

0.90

oke

0.90

Activations Density 0.010%

references to "Hasbro" in the text

references to the brand "Hasbro."

No Comments

No Known Activations