INDEX

Explanations

phrases related to discovering or uncovering information

oai_token-act-pair · gpt-3.5-turbo

references to present situations or current events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

PLIED

-0.77

tein

-0.70

stroke

-0.67

 operation

-0.66

ricular

-0.64

 teammates

-0.63

 sabotage

-0.62

 portfolio

-0.59

obbies

-0.59

ihad

-0.59

POSITIVE LOGITS

 ourselves

1.12

 witnessing

0.84

 electing

0.82

 glimpse

0.81

 glimps

0.79

ankind

0.76

Episode

0.76

 reckoning

0.75

ometers

0.74

 incarcer

0.74

Activations Density 0.325%

phrases related to discovering or uncovering information

references to present situations or current events

No Comments

No Known Activations