INDEX

Explanations

references to user profiles, particularly in the context of online platforms like LinkedIn

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

__':

-0.91

 calculées

-0.90

AutoScaleMode

-0.85

principalColumn

-0.78

 Cranston

-0.76

__":

-0.72

 tóxic

-0.71

ocarcinoma

-0.71

 Beginnings

-0.70

 bền

-0.70

POSITIVE LOGITS

 profiles

2.08

 profile

2.06

 Profile

1.97

 Profiles

1.84

 PROFILE

1.78

Profiles

1.78

profile

1.77

PROFILE

1.75

profiles

1.73

Profile

1.71

Activations Density 0.036%

references to user profiles, particularly in the context of online platforms like LinkedIn

No Comments

No Known Activations