INDEX

Explanations

referencing and qualifying statements related to particular contexts in discussions about behavior or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

them

-0.82

Them

-0.80

 THEM

-0.78

 őket

-0.69

 Them

-0.67

 henne

-0.67

 honom

-0.66

これを

-0.65

 jambes

-0.63

lui

-0.63

POSITIVE LOGITS

 there

1.62

 they

1.18

we

1.10

the

1.02

there

0.95

 individuals

0.85

)";

0.85

 certain

0.84

)");

0.84

it

0.82

Activations Density 1.331%

referencing and qualifying statements related to particular contexts in discussions about behavior or actions

No Comments

No Known Activations