INDEX

Explanations

phrases that refer to solutions or resolutions to problems or equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

IntoConstraints

-0.80

Efq

-0.78

 Theſe

-0.62

 virtuel

-0.58

 myſelf

-0.57

 auffi

-0.56

thenReturn

-0.56

 ImGui

-0.55

 Majefty

-0.55

$_"

-0.54

POSITIVE LOGITS

 solve

1.68

 Solve

1.63

 solutions

1.63

 solution

1.62

 solves

1.58

 solved

1.51

 solving

1.51

solve

1.50

Solve

1.50

 Solving

1.50

Activations Density 0.491%

phrases that refer to solutions or resolutions to problems or equations

No Comments

No Known Activations