INDEX

Explanations

instructions or steps in a process

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the initial steps or actions in a process

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

sung

-0.80

raph

-0.75

sports

-0.73

bos

-0.69

ancies

-0.68

rw

-0.68

rams

-0.64

ween

-0.62

cats

-0.62

Sleep

-0.61

POSITIVE LOGITS

 foremost

0.82

imester

0.81

 introdu

0.72

 Coinbase

0.71

 hurdle

0.71

 checkout

0.70

 steps

0.70

 responders

0.70

 prerequisite

0.66

oyer

0.66

Activations Density 0.084%

instructions or steps in a process

phrases indicating the initial steps or actions in a process

No Comments

No Known Activations