INDEX

Explanations

references to actions or situations that are considered gratifying

oai_token-act-pair · gpt-3.5-turbo

terms related to gratification and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aan

-0.79

ez

-0.78

oÄŁ

-0.77

anos

-0.75

ey

-0.75

icut

-0.74

away

-0.73

ese

-0.72

rio

-0.72

icted

-0.71

POSITIVE LOGITS

tesy

0.91

uitous

0.88

TRY

0.86

ULTS

0.84

ãĥ£

0.83

CONT

0.76

 sidx

0.75

++++

0.74

 icing

0.72

 guiActiveUn

0.72

Activations Density 0.081%

references to actions or situations that are considered gratifying

terms related to gratification and its variations

No Comments

No Known Activations