INDEX

Explanations

terms related to value or numerical assessment

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

The token "value" and related terms

np_acts-logits-general · gemini-2.0-flash

value and its contexts

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AnchorStyles

-0.67

 فريبيس

-0.66

awaiter

-0.64

ConstraintMaker

-0.64

 Superhosts

-0.61

Personendaten

-0.60

 ISNI

-0.59

ness

-0.58

 kautta

-0.58

"](

-0.58

POSITIVE LOGITS

 values

1.11

 Values

0.96

values

0.94

 value

0.90

Values

0.85

值

0.83

값

0.82

 getValue

0.82

 proposition

0.81

 Value

0.80

Activations Density 0.128%

terms related to value or numerical assessment

The token "value" and related terms

value and its contexts

No Comments

No Known Activations