INDEX

Explanations

positive events or achievements

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>

-2.17

-0.74

/**

-0.66

ⓧ

-0.64

<?

-0.62

 bestow

-0.61

 knelt

-0.60

 exert

-0.59

//---

-0.57

 beseech

-0.57

POSITIVE LOGITS

 saar

1.20

 jaya

1.16

 lele

1.11

 seksi

1.06

 Minang

1.05

 kasa

1.05

 saha

0.98

 kaos

0.97

 salat

0.96

 jawa

0.94

Activations Density 2.058%

positive events or achievements

No Comments

No Known Activations