INDEX

Explanations

TV shows, segments, and other entertainment-related information

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fep

-1.17

 tranf

-1.16

ftu

-1.15

 unwarran

-1.07

 fatis

-1.06

fto

-1.05

 thut

-1.05

 nece

-1.04

 pollut

-1.01

 perfon

-1.01

POSITIVE LOGITS

 comedy

1.02

 Comedy

0.93

 comedian

0.89

 comedians

0.88

comedy

0.85

 comedic

0.84

 humor

0.84

Comedy

0.79

 hilarious

0.77

 jokes

0.77

Activations Density 0.755%

TV shows, segments, and other entertainment-related information

No Comments

No Known Activations