INDEX

Explanations

references to self and personal identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 CreateTagHelper

-0.72

CodeAttribute

-0.66

-0.58

StoryboardSegue

-0.57

enterOuterAlt

-0.55

verständlich

-0.52

RegressionTest

-0.47

roek

-0.47

 resourceCulture

-0.46

CWE

-0.46

POSITIVE LOGITS

 self

4.01

self

3.82

 Self

3.36

Self

3.29

 SELF

3.00

SELF

2.83

 selves

2.70

selves

2.29

 Selbst

2.24

Selbst

1.97

Activations Density 0.184%

references to self and personal identity

No Comments

No Known Activations