INDEX

Explanations

mentions of movies and actors

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

⇨

-0.53

亘

-0.51

￣

-0.51

 المعيارى

-0.50

toBe

-0.49

BoxShadow

-0.49

Abs

-0.49

SAX

-0.48

Disk

-0.47

]<=

-0.47

POSITIVE LOGITS

 intersper

1.24

 hairc

1.16

 maneu

1.08

 unspeak

1.04

 increa

1.01

fuf

1.01

 shenan

1.01

 intermitt

1.00

 boop

0.99

 apprehen

0.98

Activations Density 0.053%

mentions of movies and actors

No Comments

No Known Activations