INDEX

Explanations

characters like ':' that separate categories or options

oai_token-act-pair · gpt-3.5-turbo

instances of division or classification into two distinct categories or types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

phi

-0.82

board

-0.72

 certs

-0.70

ãĤ´ãĥ³

-0.65

ahar

-0.64

eez

-0.62

º

-0.61

enger

-0.61

nexus

-0.61

Ł

-0.60

POSITIVE LOGITS

 Firstly

0.94

 namely

0.94

 halves

0.88

viz

0.88

 sexes

0.82

 totaling

0.71

Firstly

0.70

 apiece

0.67

 thirds

0.67

hemat

0.67

Activations Density 0.268%

characters like ':' that separate categories or options

instances of division or classification into two distinct categories or types

No Comments

No Known Activations