INDEX

Explanations

causal relationships involving leading to effects or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

'{@

-0.70

 batalha

-0.67

 tros

-0.66

 strå

-0.65

styleable

-0.65

 apparti

-0.65

ValueStyle

-0.65

 Trabal

-0.59

 escuchadas

-0.59

 bParam

-0.59

POSITIVE LOGITS

 eventual

0.83

 resulted

0.83

 caused

0.81

 terjadinya

0.81

 resulting

0.81

 increased

0.79

 causes

0.78

caused

0.76

0.74

导致

0.73

Activations Density 0.343%

causal relationships involving leading to effects or outcomes

No Comments

No Known Activations