INDEX

Explanations

the symbol '-' indicating lists or negative items

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.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>

-2.27

ⓧ

-0.77

 implement

-0.61

-0.60

get

-0.60

 butterknife

-0.60

-0.59

<eos>

-0.59

in

-0.59

put

-0.59

POSITIVE LOGITS

 wien

1.74

 affor

1.73

 lele

1.68

 accla

1.66

 volunte

1.64

 coö

1.64

 emphat

1.63

 unlaw

1.63

 maneu

1.63

 increa

1.60

Activations Density 0.105%

the symbol '-' indicating lists or negative items

No Comments

No Known Activations