INDEX

Explanations

terms related to crossing or crossing off items from a list

oai_token-act-pair · gpt-3.5-turbo

references to crossing lines or boundaries, often in the context of transitions or influences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ĸļ

-0.79

 opted

-0.63

andum

-0.62

console

-0.61

 avail

-0.61

 secure

-0.60

err

-0.60

undle

-0.60

Dispatch

-0.60

ahar

-0.60

POSITIVE LOGITS

 crosses

2.87

 influences

2.23

 touches

1.59

 alters

1.34

 converts

1.21

 mixes

1.21

 casts

1.20

 scares

1.19

 embraces

1.18

 shines

1.15

Activations Density 0.029%

terms related to crossing or crossing off items from a list

references to crossing lines or boundaries, often in the context of transitions or influences

No Comments

No Known Activations