INDEX

Explanations

references to the word "bath" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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



-0.90

^(@)

-0.77

-------

-0.73

 "..\..\..\

-0.69

('/:

-0.68

ductory

-0.68

مراجع

-0.68

 AssemblyProduct

-0.68

kháu

-0.67

 beginnetje

-0.67

POSITIVE LOGITS

 shield

0.93

 Shield

0.85

Shield

0.82

 bath

0.77

 boot

0.71

md

0.71

dep

0.67

 shields

0.66

SD

0.65

Dep

0.64

Activations Density 0.053%

references to the word "bath" and its variations

No Comments

No Known Activations