INDEX

Explanations

names and mentions of individuals

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

BufferException

-0.59

Precautionary

-0.54

 вос

-0.50

 last

-0.47

But

-0.46

 running

-0.44

last

-0.44

script

-0.44

 after

-0.43

 save

-0.42

POSITIVE LOGITS

انيف

0.82

:][

0.76

Hauptartikel

0.74

 FontWeight

0.72

expandindo

0.70

CodedInputStream

0.70

bleshooting

0.64

'],

0.64

 invokingState

0.64

IndentedString

0.64

Activations Density 0.217%

names and mentions of individuals

No Comments

No Known Activations