INDEX

Explanations

words related to forms or shapes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the suffix "orm" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lder

-0.70

 franc

-0.67

FTA

-0.64

 liberals

-0.63

 documenting

-0.60

 arsenic

-0.58

Hay

-0.58

 Syri

-0.58

 litter

-0.57

 Bolivia

-0.56

POSITIVE LOGITS

ammu

1.05

etheus

0.97

ouse

0.92

ingo

0.91

ativity

0.91

essage

0.90

orph

0.90

otive

0.90

sg

0.89

spring

0.87

Activations Density 0.038%

words related to forms or shapes

occurrences of the suffix "orm" in various contexts

No Comments

No Known Activations