INDEX

Explanations

instances of textual data related to plans, arrangements, or hypothetical situations, typically involving discussions about future events or possibilities

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>

-2.95

 intersper

-1.06

<?

-0.78

 endow

-0.76

 snoopy

-0.75

 shenan

-0.75

/**

-0.74

 yoda

-0.73

 gild

-0.73

ⓧ

-0.72

POSITIVE LOGITS

 monaster

0.85

 gubern

0.81

 marea

0.78

 coû

0.76

 maig

0.72

 ideolog

0.72

 utop

0.71

 conflic

0.71

 patata

0.71

 kosme

0.70

Activations Density 0.209%

instances of textual data related to plans, arrangements, or hypothetical situations, typically involving discussions about future events or possibilities

No Comments

No Known Activations