INDEX

Explanations

references to lines and segments in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

GEBURTSDATUM

-0.57

BeginContext

-0.55

 VizieR

-0.55

 createSlice

-0.54

lund

-0.52

Ngb

-0.51

 Particular

-0.49

cessed

-0.47

 nahilalakip

-0.47

interopRequire

-0.47

POSITIVE LOGITS

backers

0.78

weaver

0.65

ups

0.65

principalTable

0.64

backer

0.64

arised

0.62

Бахар

0.61

IsMutable

0.60

 drawn

0.60

feed

0.59

Activations Density 0.235%

references to lines and segments in a structured format

No Comments

No Known Activations