INDEX

Explanations

references to people and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

DllImport

-0.74

 onPostExecute

-0.69

 mourut

-0.67

 knelt

-0.65



-0.64

IndentedString

-0.61

 pleaſure

-0.59

ждены

-0.58

 sağlar

-0.58

 aveug

-0.58

POSITIVE LOGITS

 people

1.41

 folks

1.30

ppl

1.08

 everybody

1.06

 everyone

1.00

 anybody

0.97

 things

0.95

people

0.95

 anyone

0.94

 someone

0.93

Activations Density 0.118%

references to people and their interactions

No Comments

No Known Activations