INDEX

Explanations

technical terms and abbreviations in a text related to technology or academia

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

Eksteraj

-0.74

Biografía

-0.74

Ilustra

-0.74

Alguna

-0.73

Muerte

-0.70

Pued

-0.69

Todavía

-0.68

Història

-0.68

Conclusión

-0.67

Producción

-0.66

POSITIVE LOGITS

 disagre

1.49

 maneu

1.44

 intersper

1.43

 reluct

1.42

 disreg

1.42

 apprehen

1.40

 impra

1.34

 scrat

1.34

 suscep

1.34

 cushi

1.28

Activations Density 0.034%

technical terms and abbreviations in a text related to technology or academia

No Comments

No Known Activations