INDEX

Explanations

references to authority figures or leadership roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Twit

-0.57

 écl

-0.52

 novios

-0.52

Writable

-0.51

 armées

-0.48

brigens

-0.48

 vast

-0.48

vil

-0.48

 Loom

-0.48

ęb

-0.47

POSITIVE LOGITS

 controllers

0.90

 beginnetje

0.85

 controller

0.84

Portale

0.82

 nakalista

0.81

AutoScaleMode

0.75

 Controllers

0.73

 Controller

0.72

 Belgi

0.70

 yours

0.70

Activations Density 0.037%

references to authority figures or leadership roles in various contexts

No Comments

No Known Activations