INDEX

Explanations

occurrences of the word "said" in sentences

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

 anse

-0.79

 solidar

-0.77

 utop

-0.75

 gero

-0.73

 robus

-0.72

 reger

-0.71

 palet

-0.69

 tenden

-0.67

 ideolog

-0.67

/**

-0.65

POSITIVE LOGITS

 they

0.56

 said

0.56

 głó

0.54

its

0.53

 fréquent

0.50

 unspeak

0.50

said

0.49

 gaily

0.49

憾

0.48

it

0.48

Activations Density 0.182%

occurrences of the word "said" in sentences

No Comments

No Known Activations