INDEX

Explanations

programming constructs or syntax elements related to assignment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelf

-0.96

 faſt

-0.96

 ſever

-0.92

 ſch

-0.90

 ſta

-0.89

 Houſe

-0.87

 houſe

-0.85

 raiſ

-0.84

 pleaſure

-0.83

 ſche

-0.82

POSITIVE LOGITS

1.13

0.63

:=

0.60

+=

0.59

=\

0.58

|=

0.56

return

0.55

.=

0.55

}}=\

0.55

&=

0.50

Activations Density 0.153%

programming constructs or syntax elements related to assignment

No Comments

No Known Activations