INDEX

Explanations

references to governmental or administrative actions

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

TestingModule

-0.85

 CreateTagHelper

-0.79

 виправивши

-0.75

 للمعارف

-0.66

Hochspringen

-0.64

Autoritní

-0.61

SourceChecksum

-0.60

 كومونز

-0.60

 referenties

-0.59

abestanden

-0.59

POSITIVE LOGITS

 according

0.92

 said

0.81

 says

0.68

according

0.68

said

0.62

 ifølge

0.60

diğini

0.60

 noted

0.59

 según

0.58

she

0.55

Activations Density 0.152%

references to governmental or administrative actions

No Comments

No Known Activations

references to governmental or administrative actions

No Comments

No Known Activations