INDEX

Explanations

instances of numerical values or counts related to results or matches

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>

-1.76

Fordítás

-0.75

#![

-0.72

CodeAttribute

-0.69

glBindBuffer

-0.69

BeforeMethod

-0.69

glTranslatef

-0.66

 Chwiliwch

-0.65

Continuar

-0.64

 ***!

-0.63

POSITIVE LOGITS

 impra

1.40

 maneu

1.38

 disagre

1.30

 jaya

1.24

 excru

1.19

 tolerably

1.18

 suscep

1.16

 reluct

1.15

 practition

1.14

 emphat

1.09

Activations Density 0.136%

instances of numerical values or counts related to results or matches

No Comments

No Known Activations