INDEX

Explanations

occurrences of various levels, dimensions, or categories 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FormTagHelper

-0.57

HasColumnName

-0.56

drawString

-0.56

govine

-0.53

awaiter

-0.51

“

-0.51

HasForeignKey

-0.51

 AssemblyTitle

-0.50

viewBox

-0.50

Mun

-0.50

POSITIVE LOGITS

 pleaſure

0.87

 Jefus

0.81

 Monfieur

0.81

 Majefty

0.79

 itſelf

0.75

AndEndTag

0.73

 tiegħek

0.73

 poffible

0.72

 Theſe

0.71

 themſelves

0.71

Activations Density 0.636%

occurrences of various levels, dimensions, or categories in different contexts

No Comments

No Known Activations