INDEX

Explanations

phrases related to different countries or regions

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Republic."

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

TERN

-0.90

ãĤ¤

-0.80

balls

-0.75

ritch

-0.73

Ir

-0.72

TER

-0.72

Oracle

-0.71

::::::::

-0.68

berger

-0.68

NING

-0.66

POSITIVE LOGITS

 Republic

1.13

Republic

1.00

oslov

0.91

 republic

0.90

rats

0.89

naire

0.84

 Seym

0.76

ans

0.76

aine

0.75

ribution

0.70

Activations Density 0.023%

phrases related to different countries or regions

mentions of the term "Republic."

No Comments

No Known Activations