INDEX

Explanations

terms related to forests and forestry

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

-0.58

di

-0.55

co

-0.54

be

-0.53

</strong>

-0.53

Les

-0.51

app

-0.49

do

-0.49

-0.48

mis

-0.48

POSITIVE LOGITS

ImageContext

1.01

bootstrapcdn

0.97

/*---

0.96

 greateſt

0.95

 purpoſe

0.92

 Reſ

0.92

 Chriftian

0.91

SequentialGroup

0.91

 pleaſure

0.90

BASELINE

0.88

Activations Density 0.061%

terms related to forests and forestry

No Comments

No Known Activations