INDEX

Explanations

causal explanations or reasons for statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

pergillus

-0.59

 Mazar

-0.59

 thác

-0.54

Kesimpulan

-0.50

vaux

-0.49

ilanth

-0.48

 BrowserModule

-0.47

ServletConfig

-0.47

bewerken

-0.47

 airfoil

-0.47

POSITIVE LOGITS

Since

1.05

Because

1.05

скольку

1.00

 Since

0.97

 Because

0.94

由于

0.94

Due

0.88

oarece

0.86

由於

0.85

Karena

0.85

Activations Density 0.168%

causal explanations or reasons for statements

No Comments

No Known Activations