INDEX

Explanations

specific numbers or numerical patterns

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.01

ⓧ

-0.78

GEBURTSDATUM

-0.77

 springfox

-0.74

abestanden

-0.74

 agrí

-0.73

rawDesc

-0.73

AddTagHelper

-0.72

 wireType

-0.70

 ivelany

-0.70

POSITIVE LOGITS

 maneu

1.64

 affor

1.61

 impra

1.60

 reluct

1.57

 unlaw

1.55

 increa

1.55

 inev

1.48

 guarante

1.44

 Augu

1.44

 strick

1.43

Activations Density 0.275%

specific numbers or numerical patterns

No Comments

No Known Activations