INDEX

Explanations

references to cheerleading and related events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.35

Lato

-0.71

calciatore

-0.67

ClientSize

-0.67

glMatrixMode

-0.66

 المعرف

-0.64

AutoScaleMode

-0.63

glTexCoord

-0.62

Сло

-0.62

 كومونز

-0.61

POSITIVE LOGITS

 cheer

1.46

 Cheer

1.41

Cheer

1.37

cheer

1.31

 bandung

1.30

 chrysler

1.26

 eiffel

1.23

 beverly

1.23

 cheering

1.22

 cheerleader

1.21

Activations Density 0.419%

references to cheerleading and related events

No Comments

No Known Activations