INDEX

Explanations

imperative verbs indicating actions or instructions

oai_token-act-pair · gpt-3.5-turbo

commands or suggestions made to an audience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

éĹ

-0.64

 breaching

-0.61

 wheelchair

-0.61

ITE

-0.61

 bottleneck

-0.60

PATH

-0.60

 record

-0.60

ELF

-0.59

mith

-0.58

cler

-0.58

POSITIVE LOGITS

ings

1.00

 Yourself

0.86

ership

0.85

quartered

0.82

ington

0.82

 yourselves

0.81

anon

0.80

amaz

0.79

 Quote

0.79

ables

0.77

Activations Density 0.205%

imperative verbs indicating actions or instructions

commands or suggestions made to an audience

No Comments

No Known Activations