INDEX

Explanations

words related to the term "alpha"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "alpha" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Ö¼

-0.99

ROR

-0.89

ringe

-0.79

enance

-0.78

Created

-0.78

enegger

-0.77

AMI

-0.76

alities

-0.73

travel

-0.72

LAND

-0.72

POSITIVE LOGITS

 Centauri

1.10

 alpha

0.97

 males

0.82

 male

0.82

 fide

0.75

 blocker

0.72

 blockers

0.71

 guarding

0.71

 beta

0.71

cephal

0.70

Activations Density 0.006%

words related to the term "alpha"

occurrences of the term "alpha" in various contexts

No Comments

No Known Activations