INDEX

Explanations

phrases related to objectivity or facts

oai_token-act-pair · gpt-3.5-turbo

references to objectives and goal-oriented metrics

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

 Tycoon

-0.88

oles

-0.84

ulet

-0.79

letters

-0.79

olini

-0.78

oly

-0.78

buck

-0.76

bowl

-0.73

bird

-0.72

corn

-0.72

POSITIVE LOGITS

 Objective

0.92

 observer

0.90

ives

0.88

ignty

0.86

 objective

0.84

itatively

0.76

 appraisal

0.74

 guiActiveUn

0.74

isable

0.71

 measurement

0.71

Activations Density 0.021%

phrases related to objectivity or facts

references to objectives and goal-oriented metrics

No Comments

No Known Activations