INDEX

Explanations

expressions of personal insecurity or self-deprecation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

}}/>

-0.55

vitt

-0.54

SerializedSize

-0.51

 stället

-0.50

-0.46

writeFieldEnd

-0.45

 medewerkers

-0.45

hyrchwyd

-0.45

}),

-0.44

CodedInputStream

-0.44

POSITIVE LOGITS

 myself

0.91

MethodManager

0.80

myself

0.74

 myſelf

0.70

 Myself

0.66

AddTagHelper

0.66

 clumsy

0.64

 foolish

0.61

 stupid

0.60

 inept

0.57

Activations Density 0.284%

expressions of personal insecurity or self-deprecation

No Comments

No Known Activations