INDEX

Explanations

indications of decrease or low values

oai_token-act-pair · gpt-3.5-turbo

terms related to reductions or decreases in various contexts and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ocratic

-0.72

ansas

-0.71

rs

-0.70

Nev

-0.68

Pros

-0.66

NB

-0.66

istle

-0.65

rish

-0.65

nostic

-0.65

DOM

-0.65

POSITIVE LOGITS

ipop

0.79

ascus

0.71

 elimination

0.65

âĶĢâĶĢ

0.65

dylib

0.64

LOAD

0.64

 decrease

0.62

profit

0.61

eco

0.61

cules

0.61

Activations Density 0.030%

indications of decrease or low values

terms related to reductions or decreases in various contexts and statistics

No Comments

No Known Activations