INDEX

Explanations

instances where the term "scope" is mentioned in context

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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

ⓧ

-0.64

/*

-0.60

<?

-0.57

/**

-0.55

twimg

-0.54

GETHER

-0.51

 appeared

-0.50

 disarm

-0.48

 appear

-0.47

POSITIVE LOGITS

 scope

3.11

 Scope

2.91

scope

2.78

 scopes

2.74

Scope

2.61

 SCOPE

2.26

SCOPE

2.15

scopes

2.06

Scopes

1.92

 scoped

1.80

Activations Density 0.181%

instances where the term "scope" is mentioned in context

No Comments

No Known Activations