INDEX

Explanations

movie titles in a list or catalog format

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

 apprehen

-0.81

 gaily

-0.74

 impractica

-0.73

 shenan

-0.72

 unlaw

-0.71

 murmuring

-0.71

 rascal

-0.70

 impelled

-0.69

 reluct

-0.66

 reconno

-0.65

POSITIVE LOGITS

Formazione

0.74

Caratter

0.72

Oltre

0.64

Voci

0.61

 Kategor

0.61

Caratteristiche

0.58

 ejus

0.57

Più

0.57

Inoltre

0.56

 nomine

0.56

Activations Density 0.152%

movie titles in a list or catalog format

No Comments

No Known Activations