INDEX

Explanations

markers of storytelling and narrative structure within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 Autorisations

-0.66

 ModelExpression

-0.62

expandindo

-0.62

UnusedPrivate

-0.61

tagHelperRunner

-0.61

 ſch

-0.59

IntoConstraints

-0.59

ſelves

-0.59

ſelf

-0.59

 kaarangay

-0.58

POSITIVE LOGITS

'},

0.38

 precum

0.37

'],

0.35

$}}

0.35

gründ

0.34

 bParam

0.33

$/,

0.32

 Donahue

0.31

%%

0.31

bkz

0.31

Activations Density 0.039%

markers of storytelling and narrative structure within documents

No Comments

No Known Activations