INDEX

Explanations

words related to resolution and problem-solving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 œuvres

-0.66

 copertura

-0.63

actus

-0.63

 Suarez

-0.63

arez

-0.62

 éduc

-0.62

tagHelper

-0.61

 italiane

-0.61

изнь

-0.60

POSITIVE LOGITS

 Resolve

1.15

 resolutions

1.07

 Resolver

1.05

 AssemblyVersion

1.05

 Resolved

1.02

olving

1.00

RESOLVED

0.98

 resolution

0.96

 resolved

0.95

 Domini

0.95

Activations Density 0.054%

words related to resolution and problem-solving

No Comments

No Known Activations