INDEX

Explanations

information or steps in a set of instructions

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>

-2.41

if

-0.72

public

-0.71

 assume

-0.67

if

-0.67

若

-0.64

יע

-0.63

 look

-0.63

case

-0.62

be

-0.62

POSITIVE LOGITS

 emphat

1.89

Juf

1.83

 guarante

1.74

 Augu

1.73

 maneu

1.71

aen

1.70

 accla

1.69

fta

1.67

 inev

1.67

 squa

1.66

Activations Density 0.736%

information or steps in a set of instructions

No Comments

No Known Activations