INDEX

Explanations

actions related to assessment, selection, and determination in various contexts

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

before or related to "choice" or "select"

np_acts-logits-general · gemini-2.0-flash

choosing appropriate options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.74

országban

-0.73

oredCriteria

-0.71

ValueStyle

-0.69

aarrggbb

-0.67

Rptr

-0.62

 发表于

-0.59

 оригіналу

-0.56

ViewFeatures

-0.56

RUnlock

-0.56

POSITIVE LOGITS

 appropriate

1.19

 suitable

1.17

 Appropriate

1.04

how

0.97

 optimal

0.97

 geeigne

0.94

Appropriate

0.94

suitable

0.94

 acceptable

0.93

appropriate

0.93

Activations Density 0.607%

actions related to assessment, selection, and determination in various contexts

before or related to "choice" or "select"

choosing appropriate options

No Comments

No Known Activations