INDEX

Explanations

words related to war, conflict, and distortion

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 republi

-0.70

 praktik

-0.66

 kandid

-0.64

 pól

-0.64

 gius

-0.60

 Kün

-0.60

 trö

-0.59

 biograf

-0.58

 granat

-0.58

 Städ

-0.57

POSITIVE LOGITS

 twist

0.85

 bend

0.82

 bending

0.80

 bends

0.79

 twisting

0.79

 twisted

0.79

 bent

0.78

 distorted

0.77

 twists

0.76

 distortion

0.74

Activations Density 0.143%

words related to war, conflict, and distortion

No Comments

No Known Activations