INDEX

Explanations

conditional phrases indicating hypothetical scenarios or stipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

'],$

-0.49

 كومونز

-0.49

rylic

-0.46

[]:

-0.45

tät

-0.45

Cá

-0.45

inaison

-0.45

WaitGroup

-0.44

喱

-0.44

>();

-0.44

POSITIVE LOGITS

 propOrder

0.69

URLException

0.67

 houſe

0.66

 admit

0.64

LookAnd

0.63

บ้าง

0.62

 raiſ

0.61

 doubtnut

0.61

 Pembroke

0.60

 admitting

0.60

Activations Density 0.333%

conditional phrases indicating hypothetical scenarios or stipulations

No Comments

No Known Activations