INDEX

Explanations

proper nouns and technical terms related to various topics

oai_token-act-pair · gpt-3.5-turbo

specific references to statistics, measurements, or numerical details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 defic

-0.99

 livest

-0.87

omore

-0.86

 disadvant

-0.75

uster

-0.75

 hemor

-0.75

urally

-0.75

ership

-0.70

 ingred

-0.70

ometric

-0.69

POSITIVE LOGITS

ais

0.82

FIX

0.81

hz

0.80

mia

0.80

LSD

0.77

ze

0.76

Ned

0.75

olk

0.75

nz

0.74

fx

0.73

Activations Density 0.248%

proper nouns and technical terms related to various topics

specific references to statistics, measurements, or numerical details

No Comments

No Known Activations