INDEX

Explanations

results or outcomes

oai_token-act-pair · gpt-3.5-turbo

references to results from various studies, surveys, or tests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

pload

-0.76

Versions

-0.69

ospace

-0.69

abilia

-0.69

orthy

-0.68

cko

-0.68

eller

-0.66

worm

-0.65

upp

-0.65

ãĤ¼ãĤ¦ãĤ¹

-0.64

POSITIVE LOGITS

 deliberations

1.02

 negotiations

0.97

 conversations

0.95

 consultations

0.93

 discussions

0.90

 investigations

0.88

 exhaustive

0.87

 experimentation

0.86

 painstaking

0.86

 investigation

0.84

Activations Density 0.138%

results or outcomes

references to results from various studies, surveys, or tests

No Comments

No Known Activations