INDEX

Explanations

adjectives describing a significant degree or extent

oai_token-act-pair · gpt-3.5-turbo

words related to various forms of "ability" or "capability."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

opsis

-0.85

raped

-0.83

involved

-0.81

aptic

-0.78

erva

-0.78

romy

-0.77

trak

-0.77

href

-0.76

rette

-0.75

arij

-0.74

POSITIVE LOGITS

itable

1.03

itably

0.77

 convergence

0.71

 hazard

0.69

 climates

0.69

 proportions

0.69

 mixture

0.68

 Britann

0.66

 adjustment

0.65

arial

0.64

Activations Density 0.010%

adjectives describing a significant degree or extent

words related to various forms of "ability" or "capability."

No Comments

No Known Activations