INDEX

Explanations

words related to instructions or technical documentation

oai_token-act-pair · gpt-3.5-turbo

prepositions and words relating to location or direction

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

efully

-0.74

Â¯

-0.68

paio

-0.68

alore

-0.67

lease

-0.67

peat

-0.66

ofi

-0.65

democratic

-0.64

jri

-0.63

 reps

-0.62

POSITIVE LOGITS

 Scene

1.07

 Characters

1.00

 Events

0.98

 Past

0.98

 Transcript

0.97

 Translation

0.97

 Ends

0.95

 Plays

0.94

 Announce

0.93

 Regions

0.93

Activations Density 0.338%

words related to instructions or technical documentation

prepositions and words relating to location or direction

No Comments

No Known Activations