INDEX

Explanations

words related to adventurous activities or experiences

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

Negative Logits

<bos>

-3.21

ⓧ

-0.84

HasIndex

-0.73

hline

-0.71

public

-0.70

HasAnnotation

-0.68

HasColumnType

-0.67

<?

-0.67

has

-0.67

POSITIVE LOGITS

 lele

1.89

fta

1.89

 bandung

1.89

 scrat

1.87

 increa

1.87

 stockholm

1.86

 jaya

1.86

 wien

1.85

 impra

1.84

Juf

1.82

Activations Density 0.163%

words related to adventurous activities or experiences

No Known Activations