INDEX

Explanations

phrases related to fan reactions and interactions

oai_token-act-pair · gpt-3.5-turbo

mentions or references to fans and their engagement or reactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

tein

-0.69

 Morning

-0.62

 sunrise

-0.62

abus

-0.62

abad

-0.60

 Labrador

-0.60

 Territ

-0.60

 spac

-0.59

Nep

-0.59

Khe

-0.59

POSITIVE LOGITS

erv

1.12

hip

1.10

atics

1.06

haw

1.04

ubs

1.03

atical

1.03

hips

0.98

boys

0.94

peak

0.92

atically

0.91

Activations Density 0.041%

phrases related to fan reactions and interactions

mentions or references to fans and their engagement or reactions

No Comments

No Known Activations