INDEX

Explanations

references to policies and policy-making

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

-0.71

AndFlush

-0.66

 innamor

-0.66

 freckles

-0.64

 vermelhas

-0.63

żd

-0.61

ftagPool

-0.61

 brancas

-0.60

 GenerationType

-0.60

ANTAGES

-0.59

POSITIVE LOGITS

 policy

3.94

 Policy

3.68

Policy

3.53

policy

3.52

 POLICY

3.35

POLICY

3.18

 policies

3.14

 Policies

2.82

Policies

2.65

policies

2.55

Activations Density 0.059%

references to policies and policy-making

No Comments

No Known Activations