INDEX

Explanations

terms related to concepts of quality or categorization in context

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>

-2.43

 consultato

-0.87

+#+#

-0.82

 gyhoeddwyd

-0.79

-0.78

ValueGenerated

-0.77

rungsseite

-0.76

DebuggerNonUser

-0.75

rrggbb

-0.73

、

-0.72

POSITIVE LOGITS

aen

1.99

 emphat

1.98

 napoli

1.97

 Minang

1.91

 affor

1.88

fta

1.88

Juf

1.84

 accla

1.82

 suspic

1.82

 inev

1.82

Activations Density 0.698%

terms related to concepts of quality or categorization in context

No Comments

No Known Activations