INDEX

Explanations

phrases related to setting limits or constraints

oai_token-act-pair · gpt-3.5-turbo

indicators of limitations and restrictions

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

 à¤

-0.87

 Ãī

-0.76

ink

-0.76

heet

-0.71

FORE

-0.70

ublic

-0.66

ricks

-0.65

mary

-0.65

ILL

-0.64

çīĪ

-0.64

POSITIVE LOGITS

 scope

0.99

 allowable

0.89

 permissible

0.87

 limits

0.86

 availability

0.85

 powers

0.85

 liability

0.84

 exclus

0.82

 confines

0.82

 tolerance

0.81

Activations Density 0.208%

phrases related to setting limits or constraints

indicators of limitations and restrictions

No Comments

No Known Activations