INDEX

Explanations

terms related to engines or engine components

oai_token-act-pair · gpt-3.5-turbo

references to engines or engine-related topics

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

laus

-0.93

istani

-0.87

atana

-0.82

Ń·

-0.79

soever

-0.77

imedia

-0.76

 Childhood

-0.73

ties

-0.73

 Jagu

-0.71

oslov

-0.71

POSITIVE LOGITS

 powering

0.94

 compartment

0.84

 ignition

0.81

 braking

0.79

 horsepower

0.78

 powered

0.78

 engine

0.76

bay

0.74

 prope

0.74

 combustion

0.73

Activations Density 0.023%

terms related to engines or engine components

references to engines or engine-related topics

No Comments

No Known Activations