INDEX

Explanations

specific mentions or discussions of different versions, adaptations, or modifications of things

oai_token-act-pair · gpt-3.5-turbo

terms related to types or forms of variations

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

ħĭ

-0.79

lins

-0.78

lehem

-0.75

yer

-0.74

friends

-0.71

yers

-0.69

zers

-0.69

shire

-0.69

Ķ

-0.67

uster

-0.67

POSITIVE LOGITS

 thereof

0.95

arily

0.86

 variants

0.86

 allele

0.85

 variations

0.79

vari

0.78

arios

0.78

 spelling

0.78

dayName

0.77

 variant

0.75

Activations Density 0.027%

specific mentions or discussions of different versions, adaptations, or modifications of things

terms related to types or forms of variations

No Comments

No Known Activations