INDEX

Explanations

dates at which significant events occurred

oai_token-act-pair · gpt-3.5-turbo

references to specific years and notable events tied to those years

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ources

-0.87

rients

-0.80

bars

-0.74

oxide

-0.74

terday

-0.73

paces

-0.73

bags

-0.72

 lately

-0.70

ource

-0.69

avascript

-0.69

POSITIVE LOGITS

 edition

1.02

 Nobel

0.99

 masterpiece

0.88

 incarnation

0.84

 iteration

0.83

 Pulitzer

0.83

-'

0.82

 version

0.80

 Chevy

0.76

 Chevrolet

0.76

Activations Density 0.091%

dates at which significant events occurred

references to specific years and notable events tied to those years

No Known Activations