INDEX

Explanations

mentions of group affiliations or memberships

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.89

 Obamacare

-0.81

Nuorodos

-0.80

WithIOException

-0.78

UVWXYZ

-0.78

]--;

-0.77

EIS

-0.77

zzleHttp

-0.77

 Gret

-0.76

GLY

-0.75

POSITIVE LOGITS

 members

2.34

 member

2.32

members

2.10

 Members

2.08

member

2.04

 Member

2.02

Members

1.98

Member

1.94

 MEMBER

1.86

 MEMBERS

1.83

Activations Density 0.054%

mentions of group affiliations or memberships

No Comments

No Known Activations