INDEX

Explanations

headers or structural elements in the text

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

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

+#+#

-0.67

haped

-0.61

談社

-0.60

 marquées

-0.59

AndEndTag

-0.57

AutoScaleMode

-0.57

astify

-0.57

 élas

-0.56

ElementException

-0.56

írus

-0.56

POSITIVE LOGITS

 structure

0.78

 profile

0.78

 regime

0.77

 scheme

0.74

 pattern

0.69

 configuration

0.67

 situation

0.67

 regimen

0.66

 parameters

0.65

 trajectory

0.65

Activations Density 1.750%

headers or structural elements in the text

No Comments

No Known Activations