INDEX

Explanations

code snippets and programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 itſelf

-1.22

 myſelf

-1.04

Personendaten

-1.04

 pleaſure

-0.96

 doubtnut

-0.94

 }}$}

-0.91

 photolibrary

-0.91

 ſever

-0.91

 auffi

-0.91

 ſche

-0.91

POSITIVE LOGITS

0.60

cas

0.60

qu

0.56

0.55

0.53

Ar

0.52

At

0.52

Activations Density 0.277%

code snippets and programming concepts

No Comments

No Known Activations

code snippets and programming concepts

No Comments

No Known Activations