INDEX

Explanations

specific terms related to items or products

oai_token-act-pair · gpt-3.5-turbo

references to items or objects in various contexts

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

orks

-0.85

creen

-0.69

enthal

-0.66

hirt

-0.66

 Seym

-0.65

 Roads

-0.64

sburgh

-0.64

 Indies

-0.61

 Lanka

-0.60

 Tens

-0.59

POSITIVE LOGITS

ized

0.88

ious

0.88

izer

0.87

ization

0.86

istics

0.85

aclysm

0.83

iques

0.79

isations

0.75

izations

0.74

isation

0.73

Activations Density 0.020%

specific terms related to items or products

references to items or objects in various contexts

No Comments

No Known Activations