INDEX

Explanations

technical terms related to modeling and statistics

oai_token-act-pair · gpt-3.5-turbo

references to various types of models used in scientific and analytical contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

avorite

-0.90

vernment

-0.87

azar

-0.81

mare

-0.79

ulhu

-0.77

olulu

-0.75

 millenn

-0.74

emouth

-0.74

entimes

-0.73

entle

-0.71

POSITIVE LOGITS

 organism

0.78

 equations

0.76

model

0.76

 Operator

0.75

 Penal

0.70

 Models

0.69

LAB

0.68

models

0.68

hesis

0.67

 Blueprint

0.66

Activations Density 0.018%

technical terms related to modeling and statistics

references to various types of models used in scientific and analytical contexts

No Comments

No Known Activations