INDEX

Explanations

words related to positive evaluations or conditions

oai_token-act-pair · gpt-3.5-turbo

terminology related to favorable and advantageous conditions or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lang

-0.82

bus

-0.80

herer

-0.79

ainers

-0.75

agos

-0.74

hod

-0.74

ynthesis

-0.72

door

-0.71

here

-0.70

buck

-0.69

POSITIVE LOGITS

 matchups

1.03

 conditions

0.92

 favorable

0.84

ãĥ¼ãĥĨ

0.83

 climates

0.82

 matchup

0.81

 circumstance

0.80

 publicity

0.80

 favourable

0.79

 circumstances

0.77

Activations Density 0.050%

words related to positive evaluations or conditions

terminology related to favorable and advantageous conditions or evaluations

No Comments

No Known Activations