INDEX

Explanations

individuals or actors in a scenario

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

mef

-1.86

 intersper

-1.83

 secon

-1.79

buc

-1.71

 fluo

-1.68

 lyon

-1.67

ivi

-1.67

 Keny

-1.66

 increa

-1.66

 Augu

-1.66

POSITIVE LOGITS

 chose

0.82

got

0.79

 could

0.79

XmlEnum

0.78

 took

0.77

can

0.77

 cannot

0.76

 choose

0.76

had

0.74

has

0.74

Activations Density 0.215%

individuals or actors in a scenario

No Comments

No Known Activations