INDEX

Explanations

references to specific locations and numerical measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

SequentialGroup

-0.50

stdc

-0.50

aneously

-0.48

systemctl

-0.46

IntoConstraints

-0.46

felt

-0.45

etCode

-0.45

 tanto

-0.44

tanto

-0.44

 uncomment

-0.44

POSITIVE LOGITS

 then

0.72

rungsseite

0.62

 AssemblyProduct

0.61

 lalu

0.61

then

0.60

 olympique

0.57

 Herzog

0.57

 Then

0.56

 kemudian

0.54

 затем

0.53

Activations Density 0.818%

references to specific locations and numerical measurements

No Comments

No Known Activations