INDEX

Explanations

dates mentioned in historical contexts

oai_token-act-pair · gpt-3.5-turbo

dates or numerical references associated with historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zbollah

-0.65

pse

-0.64

reon

-0.63

malink

-0.62

spin

-0.59

venge

-0.59

azor

-0.59

 spin

-0.58

 boun

-0.57

 coordin

-0.57

POSITIVE LOGITS

GMT

0.95

-'

0.90

BCE

0.87

âĢ²

0.86

æŃ¦

0.84

sburg

0.84

çļ

0.75

èĪ

0.74

–

0.73

ä»£

0.73

Activations Density 0.049%

dates mentioned in historical contexts

dates or numerical references associated with historical events

No Comments

No Known Activations