INDEX

Explanations

references to identification or legal documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ſeveral

-0.77

"]];

-0.72

$_"

-0.70

 greateſt

-0.69

 pleaſure

-0.66

 endfor

-0.66

 themſelves

-0.66

 Monfieur

-0.66

 ſame

-0.65

\}\\

-0.64

POSITIVE LOGITS

id

3.60

Id

3.55

ID

3.51

id

2.83

Id

2.81

IDs

2.73

ID

2.60

ids

2.46

 getId

2.41

getId

2.40

Activations Density 0.139%

references to identification or legal documents

No Comments

No Known Activations