INDEX

Explanations

terms related to the circulation of fluids or objects

oai_token-act-pair · gpt-3.5-turbo

references to circulation, both in a literal and metaphorical sense

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ermott

-0.79

IELD

-0.75

omething

-0.75

RAG

-0.74

oug

-0.72

ASC

-0.71

ofi

-0.67

hov

-0.66

este

-0.66

orney

-0.65

POSITIVE LOGITS

 circulation

1.26

 advis

0.79

machine

0.78

 trough

0.75

icter

0.75

 circ

0.74

 gauge

0.73

 receipts

0.71

irtual

0.70

 vortex

0.69

Activations Density 0.022%

terms related to the circulation of fluids or objects

references to circulation, both in a literal and metaphorical sense

No Comments

No Known Activations