INDEX

Explanations

names of specific products or services

oai_token-act-pair · gpt-3.5-turbo

the phrase "such as" to identify examples or categories

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

itudinal

-0.69

ertodd

-0.69

emonic

-0.69

rition

-0.68

elling

-0.66

orem

-0.65

ELL

-0.65

iliate

-0.65

ribution

-0.64

wan

-0.62

POSITIVE LOGITS

ties

0.85

things

0.73

parts

0.73

ities

0.71

cond

0.68

such

0.66

odon

0.65

should

0.63

types

0.60

 minded

0.59

Activations Density 0.037%

names of specific products or services

the phrase "such as" to identify examples or categories

No Comments

No Known Activations