INDEX

Explanations

phrases related to technologies and projects

oai_token-act-pair · gpt-3.5-turbo

identifiers related to specific entities or keywords in a network or game context

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

ailability

-0.81

ensical

-0.75

 pestic

-0.75

 citiz

-0.74

ĪĴ

-0.67

ailable

-0.66

 doorstep

-0.66

 deaf

-0.66

 Roose

-0.64

demand

-0.61

POSITIVE LOGITS

espie

0.88

reau

0.86

veland

0.83

agall

0.76

ppe

0.74

utra

0.73

eton

0.72

esome

0.71

raltar

0.70

ierrez

0.69

Activations Density 0.399%

phrases related to technologies and projects

identifiers related to specific entities or keywords in a network or game context

No Comments

No Known Activations