INDEX

Explanations

phrases that signal transitions or shifts in conversation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Obras

-0.57

Arqu

-0.56

Composición

-0.56

Fech

-0.56

bró

-0.55

jint

-0.54

Fis

-0.54

Propiedades

-0.54

醐

-0.54

Programa

-0.53

POSITIVE LOGITS

 impra

1.48

 maneu

1.47

 tolerably

1.41

 gaily

1.41

 indestru

1.39

 unce

1.39

 disreg

1.33

 unspeak

1.32

 unve

1.32

 madonna

1.31

Activations Density 0.072%

phrases that signal transitions or shifts in conversation

No Comments

No Known Activations