INDEX

Explanations

capitalized words with a mix of letters and numbers

oai_token-act-pair · gpt-3.5-turbo

terms related to specific locations or institutions

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

âĢ¢âĢ¢

-0.65

 innocence

-0.64

erest

-0.63

 Archdemon

-0.62

 stead

-0.62

 hover

-0.62

 glim

-0.61

romeda

-0.60

 rusty

-0.59

 remission

-0.59

POSITIVE LOGITS

quist

0.84

opers

0.82

itte

0.77

portation

0.76

ħĭ

0.74

oves

0.74

ulence

0.73

oving

0.72

xus

0.71

aky

0.71

Activations Density 0.075%

capitalized words with a mix of letters and numbers

terms related to specific locations or institutions

No Comments

No Known Activations