INDEX

Explanations

references to the month of August

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Rè

-0.74

:+:

-0.65

#+#

-0.60

pade

-0.57

jsii

-0.57

principalTable

-0.57

/>\

-0.57

Бли

-0.56

irait

-0.56

 Mors

-0.56

POSITIVE LOGITS

ConstraintMaker

0.77

ftagPool

0.70

 geleverd

0.61

LookAnd

0.60

 admiten

0.60

 grecque

0.59

 intérieure

0.58

 nhiên

0.58

 dieťa

0.58

 igång

0.58

Activations Density 0.102%

references to the month of August

No Comments

No Known Activations