INDEX

Explanations

words related to specific geographic locations or people

oai_token-act-pair · gpt-3.5-turbo

geographical names or 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

Spoiler

-0.76

Interstitial

-0.71

pection

-0.65

SPONSORED

-0.62

 role

-0.60

 suspense

-0.60

ATTLE

-0.60

taboola

-0.60

 conditioned

-0.59

 phantom

-0.58

POSITIVE LOGITS

itsch

0.92

anski

0.86

illi

0.85

inski

0.73

geist

0.73

ovsky

0.72

oche

0.71

oos

0.71

inka

0.69

idis

0.69

Activations Density 0.119%

words related to specific geographic locations or people

geographical names or references

No Comments

No Known Activations