INDEX

Explanations

terms related to non-specific elements or characteristics 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 @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

complexContent

-0.51

ESAR

-0.50

shund

-0.49

ISODE

-0.49

ΑΙ

-0.47

formable

-0.46

PLANATION

-0.46

ption

-0.44

fycat

-0.43

arion

-0.43

POSITIVE LOGITS

+#+#

0.66

 Theſe

0.66

ſelves

0.65

 nakalista

0.62

 Mounts

0.61

 hort

0.59

$_"

0.57

WithIOException

0.57

 Noct

0.56

pec

0.54

Activations Density 0.390%

terms related to non-specific elements or characteristics in various contexts

No Comments

No Known Activations