INDEX

Explanations

proper nouns related to media and entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

tahui

-0.58

uruhan

-0.56

 INVENTION

-0.54

ederos

-0.53

 ['./

-0.51

inderung

-0.51

uxxxx

-0.51

 оригіналу

-0.50

genstein

-0.48

 Autorizaciones

-0.47

POSITIVE LOGITS

CNN

0.92

CNN

0.88

 ESPN

0.86

MTV

0.85

 MSNBC

0.79

 CNBC

0.76

NBC

0.74

 Newsweek

0.74

ESPN

0.72

HBO

0.71

Activations Density 0.244%

proper nouns related to media and entertainment

No Comments

No Known Activations