INDEX

Explanations

terms related to people, relationships, and interactions between individuals

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>

-1.63

 intersper

-0.77

<?

-0.75

ⓧ

-0.72

 encomp

-0.65

 underval

-0.63

 дописавши

-0.62

 superintend

-0.62

 apprehen

-0.60

 recollect

-0.60

POSITIVE LOGITS

Whom

1.14

whom

1.07

 whom

1.06

 Whom

0.98

 Luglio

0.93

 Ottobre

0.85

 borsa

0.83

 Giugno

0.78

GYPT

0.75

 ristor

0.75

Activations Density 0.259%

terms related to people, relationships, and interactions between individuals

No Comments

No Known Activations