INDEX

Explanations

expressions of positivity and quality related to experiences and objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

AndEndTag

-0.81

それとも

-0.64

 Lest

-0.61

كويكب

-0.60

 genannt

-0.59

 sondern

-0.59

 lest

-0.58

 Correct

-0.58

TagMode

-0.58

%");

-0.57

POSITIVE LOGITS

 considering

0.83

 especially

0.79

 compared

0.78

IMO

0.78

 honestly

0.76

considering

0.74

imo

0.74

 IMHO

0.73

ngl

0.69

especially

0.67

Activations Density 0.175%

expressions of positivity and quality related to experiences and objects

No Comments

No Known Activations