INDEX

Explanations

numerical values, particularly those typically associated with coding or mathematical computations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

extAlignment

-0.98

 '\\;'

-0.96

 ostavi

-0.92

 للمعارف

-0.88

WriteTagHelper

-0.87

 <=",

-0.82

 MenuView

-0.82

principalColumn

-0.81

 ModelExpression

-0.81

LLocation

-0.80

POSITIVE LOGITS

er

0.50

import

0.49

ով

0.45

0.43

stva

0.43

iello

0.42

ばかり

0.41

 Frank

0.41

 import

0.41

Cur

0.41

Activations Density 0.020%

numerical values, particularly those typically associated with coding or mathematical computations

No Comments

No Known Activations