INDEX

Explanations

mentions of shows and their related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

bati

-0.63

 Baltic

-0.57

DPD

-0.57

initas

-0.56

dients

-0.55

EDEFAULT

-0.55

 Fati

-0.55

mpotent

-0.54

terape

-0.54

gettyimages

-0.54

POSITIVE LOGITS

show

2.05

 Show

1.96

 show

1.95

Show

1.92

 SHOW

1.73

SHOW

1.70

 Shows

1.59

shows

1.57

 shows

1.49

Shows

1.48

Activations Density 0.129%

mentions of shows and their related contexts

No Comments

No Known Activations