INDEX

Explanations

specific measurements related to physical attributes or quantities

oai_token-act-pair · gpt-3.5-turbo

quantitative descriptions and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

apego

-0.63

oaded

-0.54

orsi

-0.53

inx

-0.51

ient

-0.51

oppable

-0.51

enegger

-0.50

uilt

-0.50

milo

-0.50

rehensive

-0.50

POSITIVE LOGITS

 guise

0.83

 context

0.82

 vicinity

0.79

 nutshell

0.75

 manner

0.75

 mode

0.73

 circles

0.72

 midst

0.69

 contexts

0.67

 vein

0.67

Activations Density 1.035%

specific measurements related to physical attributes or quantities

quantitative descriptions and statistics

No Comments

No Known Activations