INDEX

Explanations

references to "us" and related pronouns

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

 houſe

-1.18

 purpoſe

-1.07

 pleaſure

-1.07

 Houſe

-1.06

 cauſe

-1.04

 fevere

-1.03

 Monfieur

-1.02

Efq

-0.99

 ſtate

-0.97

 raiſ

-0.96

POSITIVE LOGITS

us

1.05

 them

0.92

him

0.86

Him

0.83

 Them

0.79

us

0.77

</em>

0.77

Him

0.77

 THEM

0.75

umb

0.73

Activations Density 0.126%

references to "us" and related pronouns

No Comments

No Known Activations