INDEX

Explanations

references to the term "TW" or "Thames" which could be associated with a specific topic or entity

oai_token-act-pair · gpt-3.5-turbo

references to a specific television network or media outlet

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

netflix

-0.96

hammad

-0.89

lain

-0.82

eer

-0.82

backer

-0.81

resso

-0.79

eering

-0.79

ering

-0.77

 Hamm

-0.77

gio

-0.76

POSITIVE LOGITS

TW

1.14

TW

1.08

BUR

0.88

 GOODMAN

0.82

©¶æ¥µ

0.82

 redund

0.80

pez

0.79

DEV

0.78

OY

0.78

seys

0.72

Activations Density 0.013%

references to the term "TW" or "Thames" which could be associated with a specific topic or entity

references to a specific television network or media outlet

No Comments

No Known Activations