INDEX

Explanations

actions related to determining or comparing options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Efq

-0.87

 surla

-0.77

+#+#

-0.75

Personendaten

-0.74

SourceChecksum

-0.73

 Jefus

-0.72

featureID

-0.71

principalTable

-0.71

DebuggerNonUser

-0.70

ſelves

-0.70

POSITIVE LOGITS

 then

0.56

Then

0.54

 Then

0.50

poi

0.49

✭✭

0.49

 pretend

0.48

 THEN

0.47

THEN

0.46

avedra

0.46

 relever

0.46

Activations Density 0.458%

actions related to determining or comparing options

No Comments

No Known Activations