INDEX

Explanations

terms related to measurement or estimation

oai_token-act-pair · gpt-3.5-turbo

terms related to measurement and evaluation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sis

-0.86

 Fathers

-0.85

 Kardashian

-0.76

————————

-0.74

uality

-0.72

heid

-0.70

scape

-0.70

edited

-0.69

Lay

-0.68

tic

-0.68

POSITIVE LOGITS

 gauge

1.42

gau

1.29

 buoy

0.93

 Pens

0.85

UGE

0.81

Gau

0.80

vernment

0.77

ãĤ¡

0.75

igue

0.74

 rods

0.73

Activations Density 0.009%

terms related to measurement or estimation

terms related to measurement and evaluation

No Comments

No Known Activations