INDEX

Explanations

phrases related to military operations and targets

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

<bos>

-0.47

enteuer

-0.46

 człowie

-0.45

 dziewczyn

-0.43

StoreMessageInfo

-0.43

falgar

-0.42

wardship

-0.41

Espèce

-0.41

 Gewer

-0.40

 senescence

-0.40

POSITIVE LOGITS

 Darío

0.82

 Gorb

0.80

 Diez

0.77

 Bartholo

0.74

 Mejía

0.72

 Nicolai

0.70

 Marín

0.69

 Domínguez

0.69

 Cuen

0.68

entibus

0.68

Activations Density 0.454%

phrases related to military operations and targets

No Comments

No Known Activations