INDEX

Explanations

contextually significant tokens that indicate the beginning of new sections or important elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 propOrder

-1.19



-0.96

PyExc

-0.94

rawtypes

-0.89

сылкі

-0.88

transQ

-0.88

Personendaten

-0.87

RTLD

-0.87

fjspx

-0.86

DockStyle

-0.85

POSITIVE LOGITS

be

1.44

Be

1.41

Be

1.34

BE

1.27

 Beasley

1.25

BE

1.23

 Beal

1.07

 Belich

1.06

 Bebe

0.96

abe

0.96

Activations Density 0.115%

contextually significant tokens that indicate the beginning of new sections or important elements in the text

No Comments

No Known Activations