INDEX

Explanations

proper names, particularly those of people 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 purpoſe

-2.29

 ſtate

-2.23

 myſelf

-2.17

 houſe

-2.17

 pleaſure

-2.17

 itſelf

-2.13

 raiſ

-2.13

 ſche

-2.11

 whoſe

-2.08

 ſta

-2.05

POSITIVE LOGITS

1.38

↵↵

1.31

<eos>

1.15

1.07

↵

1.04

1.00

0.97

0.93

0.92

Activations Density 0.335%

proper names, particularly those of people in various contexts

No Comments

No Known Activations