INDEX

Explanations

mentions of the term "subject" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

SPS

-0.87

 faſt

-0.76

 GenerationType

-0.75

 craw

-0.75

ForRow

-0.74

 membuk

-0.72

Efq

-0.70

 whoſe

-0.70

 limpio

-0.70

 ſta

-0.70

POSITIVE LOGITS

 subject

2.83

subject

2.58

 Subject

2.57

 subjects

2.50

Subject

2.47

 SUBJECT

2.34

 Subjects

2.26

SUBJECT

2.25

subjects

2.17

Subjects

2.10

Activations Density 0.054%

mentions of the term "subject" and its variations in different contexts

No Comments

No Known Activations