INDEX

Explanations

locations and specific details within news articles

oai_token-act-pair · gpt-3.5-turbo

specific locations and associated details within a text

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 fulfil

-0.95

 realised

-0.90

 whilst

-0.82

Firstly

-0.80

 civilisation

-0.80

 realise

-0.79

 maths

-0.78

 learnt

-0.78

 flavour

-0.77

 favour

-0.77

POSITIVE LOGITS

 statewide

0.95

 Asheville

0.92

Alert

0.88

 Boise

0.84

 Downtown

0.82

 downtown

0.81

 Outdoor

0.81

 COUNTY

0.80

 Southwest

0.80

 Wilmington

0.80

Activations Density 3.186%

locations and specific details within news articles

specific locations and associated details within a text

No Known Activations