INDEX

Explanations

acronyms related to technology and organizations

oai_token-act-pair · gpt-3.5-turbo

mentions of specific terms related to technology and significant historical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

EMENT

-0.74

IVERS

-0.73

Ago

-0.72

Interstitial

-0.68

nces

-0.67

mble

-0.67

EngineDebug

-0.67

selage

-0.66

Ü

-0.66

 Liberties

-0.66

POSITIVE LOGITS

olit

0.87

ension

0.81

stone

0.79

osit

0.79

osite

0.79

odor

0.79

ologic

0.78

ocalypse

0.77

opped

0.76

age

0.75

Activations Density 0.029%

acronyms related to technology and organizations

mentions of specific terms related to technology and significant historical references

No Comments

No Known Activations