INDEX

Explanations

statements with surprising or unexpected outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Addo

-0.55

 fallait

-0.47

"}")

-0.46

amaño

-0.45

 Faust

-0.44

meneu

-0.44

 vidare

-0.44

 Sympathi

-0.43

 fernando

-0.43

 Alve

-0.43

POSITIVE LOGITS

 surprisingly

0.96

Surprisingly

0.92

 Surprisingly

0.86

 strangely

0.84

 oddly

0.84

竟然

0.81

 weirdly

0.76

 somehow

0.74

 Somehow

0.74

 ironically

0.73

Activations Density 0.335%

statements with surprising or unexpected outcomes

No Comments

No Known Activations