INDEX

Explanations

references to reputations and the impact of actions on personal or public reputations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stdc

-0.68

horts

-0.62

atet

-0.59

 Censo

-0.58

unnitel

-0.56

iban

-0.54

allenge

-0.54

 doPost

-0.54

RepeatedField

-0.54

migrationBuilder

-0.53

POSITIVE LOGITS

 reputation

1.55

 brand

1.42

 Reputation

1.29

 reput

1.27

 branding

1.27

Reputation

1.24

 reputations

1.24

brand

1.20

 Brand

1.16

 reputa

1.11

Activations Density 0.296%

references to reputations and the impact of actions on personal or public reputations

No Comments

No Known Activations