INDEX

Explanations

references to specific historical events and individuals

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>

-2.78

 continue

-0.69

<eos>

-0.67

-0.66

HasIndex

-0.65

 confirm

-0.65

add

-0.63

 assist

-0.62

addComponent

-0.62

sit

-0.62

POSITIVE LOGITS

Juf

1.70

 bandung

1.67

 maneu

1.63

 emphat

1.61

 jaya

1.59

 maroc

1.58

 affor

1.55

 Minang

1.55

 disagre

1.53

 lele

1.53

Activations Density 1.543%

references to specific historical events and individuals

No Comments

No Known Activations