INDEX

Explanations

references to groups, names, or terms related to different forms of authority, leadership, and identity

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

'][]

-0.38

ppard

-0.37

stopPropagation

-0.36

re

-0.34

We

-0.34

awaited

-0.33

 begrü

-0.33

 early

-0.32

ADD

-0.32

POSITIVE LOGITS

bootstrapcdn

0.96

jsonwebtoken

0.94

Personensuche

0.93

 AssemblyCulture

0.90

 AssemblyTitle

0.81

Portail

0.80

protoc

0.77

interopRequire

0.76

SourceChecksum

0.76

StoryboardSegue

0.73

Activations Density 0.561%

references to groups, names, or terms related to different forms of authority, leadership, and identity

No Comments

No Known Activations