INDEX

Explanations

terms related to disability and disabled statuses

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 createSlice

-0.99

 PLWABN

-0.93

Portale

-0.92

LookAnd

-0.89

MigrationBuilder

-0.88

 صوتيه

-0.86

氓

-0.85

MessageOf

-0.84

gonic

-0.83

 CreateTagHelper

-0.82

POSITIVE LOGITS

 disability

1.93

 disabled

1.85

 disabilities

1.81

 Disability

1.77

 Disabled

1.66

 Disabilities

1.64

disabled

1.59

Disability

1.58

Disabled

1.58

 disabling

1.36

Activations Density 0.129%

terms related to disability and disabled statuses

No Comments

No Known Activations