INDEX

Explanations

occurrences of the letter 'a' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

-0.54

DebuggerStep

-0.50

<bos>

-0.47

ط

-0.47

BETH

-0.46

pp

-0.46

ں

-0.46

ই

-0.45

vskip

-0.44

openSession

-0.44

POSITIVE LOGITS

 متعلقه

0.71

ValueStyle

0.69

enumi

0.58

ee

0.57

 InputDecoration

0.56

ebs

0.56

ไง

0.54

 فريبيس

0.53

ConstraintMaker

0.53

osoba

0.53

Activations Density 0.226%

occurrences of the letter 'a' in various contexts

No Comments

No Known Activations