INDEX

Explanations

discussions related to confusion and verification in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

PREFERRED

-0.59

setopt

-0.55

 Nachteile

-0.53

 حاضر

-0.51

 parha

-0.48

ElementException

-0.46

جغرافيا

-0.45

 assoluto

-0.45

Preferred

-0.44

 life

-0.44

POSITIVE LOGITS

 maybe

1.23

 Maybe

1.21

Maybe

1.15

 Perhaps

1.12

maybe

1.09

 perhaps

1.08

Perhaps

1.02

 Possibly

1.02

perhaps

1.02

 strange

0.99

Activations Density 0.457%

discussions related to confusion and verification in communication

No Comments

No Known Activations