INDEX

Explanations

sequences of non-space characters or specific formatting cues

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

 كومونز

-0.63

ثيق

-0.51

SequentialGroup

-0.47

 ddelweddau

-0.38

Dem

-0.36

 INTERESAR

-0.36

VYMaps

-0.36

MEDIATE

-0.34

تقاوى

-0.34

 yardımcı

-0.34

POSITIVE LOGITS

featureID

0.51

httphttps

0.48

 nakalista

0.47

outSlope

0.46

weightedMode

0.46

InstrumentedTest

0.46

+#+

0.45

 חיצוניים

0.43

flashdata

0.43

 "/")

0.43

Activations Density 0.056%

sequences of non-space characters or specific formatting cues

No Comments

No Known Activations