INDEX

Explanations

terms related to cooperatives or co-ops

oai_token-act-pair · gpt-3.5-turbo

references to cooperative or collaborative terms and structures

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

 Cabrera

-0.83

=-=-

-0.81

ħ

-0.78

vous

-0.78

Ĩ

-0.76

andum

-0.75

Osw

-0.74

hner

-0.74

º

-0.73

«

-0.73

POSITIVE LOGITS

 versions

0.86

 classics

0.82

 equivalents

0.77

 media

0.74

 pursuits

0.74

 counterparts

0.73

 romance

0.71

 content

0.71

 staple

0.71

 cinem

0.70

Activations Density 0.226%

terms related to cooperatives or co-ops

references to cooperative or collaborative terms and structures

No Comments

No Known Activations