INDEX

Explanations

specific words related to policies, procedures, or options

oai_token-act-pair · gpt-3.5-turbo

terms related to cycling and options for cycling-related initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

arching

-0.82

orate

-0.80

aaa

-0.75

 guiActiveUn

-0.70

aaaa

-0.69

andel

-0.68

\\\\

-0.68

umbn

-0.65

ds

-0.64

onies

-0.64

POSITIVE LOGITS

 Ones

0.88

Day

0.79

Aid

0.79

 Control

0.78

 Tracker

0.77

 Breaker

0.77

 Eater

0.77

 Field

0.77

 Manager

0.77

 Week

0.76

Activations Density 0.290%

specific words related to policies, procedures, or options

terms related to cycling and options for cycling-related initiatives

No Comments

No Known Activations