INDEX

Explanations

words related to productivity and efficiency

oai_token-act-pair · gpt-3.5-turbo

references to productivity or productive concepts

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

obyl

-0.72

olog

-0.72

bole

-0.72

olina

-0.72

ocard

-0.70

hin

-0.68

 downed

-0.67

 ushered

-0.66

 tighter

-0.65

hani

-0.64

POSITIVE LOGITS

 productive

0.98

ãĥ¼ãĥĨ

0.84

acre

0.82

itures

0.81

rious

0.80

ctions

0.79

ative

0.79

ctive

0.76

productive

0.75

Marginal

0.74

Activations Density 0.027%

words related to productivity and efficiency

references to productivity or productive concepts

No Comments

No Known Activations