INDEX

Explanations

phrases related to hiding or concealing

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>

-2.94

ⓧ

-0.74

Vegeu

-0.68

/***

-0.68

<?

-0.64

HasColumnType

-0.64

Kontrola

-0.62

-0.61

Юлия

-0.60

got

-0.59

POSITIVE LOGITS

 wien

1.28

 stockholm

1.24

myn

1.21

 bordeaux

1.19

 maroc

1.19

 dises

1.18

 thut

1.18

 bayern

1.17

aen

1.17

fua

1.17

Activations Density 0.162%

phrases related to hiding or concealing

No Comments

No Known Activations