INDEX

Explanations

mentions of medical units or procedures related to intensive care

oai_token-act-pair · gpt-3.5-turbo

the term "intensive" in various contexts, particularly relating to care, tasks, and applications

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

 Gaddafi

-0.66

 Tsarnaev

-0.65

dylib

-0.65

flies

-0.65

çĭ

-0.62

opp

-0.61

DonaldTrump

-0.61

omsky

-0.61

PIN

-0.61

 Sharif

-0.61

POSITIVE LOGITS

 intensive

1.08

ly

1.01

intensive

0.97

mble

0.94

urally

0.82

icult

0.80

ively

0.79

entimes

0.77

ensive

0.76

rontal

0.75

Activations Density 0.009%

mentions of medical units or procedures related to intensive care

the term "intensive" in various contexts, particularly relating to care, tasks, and applications

No Comments

No Known Activations