INDEX

Explanations

medical terms or references

oai_token-act-pair · gpt-3.5-turbo

terms related to medical assistance or interventions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

TRUMP

-0.71

DOM

-0.70

 innocence

-0.70

ACK

-0.69

 indign

-0.67

avage

-0.64

OPLE

-0.63

toe

-0.63

!/

-0.63

YE

-0.63

POSITIVE LOGITS

allion

1.10

itations

1.08

iterranean

1.06

undai

1.04

itating

1.02

icum

1.00

ications

1.00

itated

0.96

med

0.96

ulla

0.91

Activations Density 0.008%

medical terms or references

terms related to medical assistance or interventions

No Comments

No Known Activations