INDEX

Explanations

items or concepts that involve comparison or evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

VERTISEMENT

-0.96

ArgsConstructor

-0.92

leſs

-0.80

ChildScrollView

-0.77

ſſen

-0.77

ſſel

-0.76

CHREIB

-0.76

 Rptr

-0.76

Lycka

-0.74

Datuak

-0.73

POSITIVE LOGITS

↵↵

1.58

↵

1.42

↵↵↵

1.24

↵↵↵↵

1.17

<eos>

1.09

[toxicity=0]

1.09

↵↵↵↵↵

1.07

↵↵↵↵↵↵

0.98

↵↵↵↵↵↵↵

0.89

↵↵↵↵↵↵↵↵↵

0.88

Activations Density 0.014%

items or concepts that involve comparison or evaluation

No Comments

No Known Activations