INDEX

Explanations

possessive pronouns and terms related to attribution

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.96

 have

-0.62

and

-0.61

}{||

-0.61

꿔

-0.60

#![

-0.59

옮

-0.59

 become

-0.58

protected

-0.58

POSITIVE LOGITS

 thut

1.68

fta

1.60

 Minang

1.57

 stockholm

1.53

hcm

1.48

Juf

1.48

 bandung

1.45

aen

1.45

 desir

1.44

fte

1.44

Activations Density 0.126%

possessive pronouns and terms related to attribution

No Comments

No Known Activations