INDEX

Explanations

terms related to the potential negative impacts or consequences of a medical treatment or substance

oai_token-act-pair · gpt-3.5-turbo

mentions of side effects and their severity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

swick

-0.71

mint

-0.70

 Patriarch

-0.68

 Knot

-0.66

 mant

-0.65

nic

-0.65

mbuds

-0.63

Rail

-0.62

gdala

-0.62

TO

-0.61

POSITIVE LOGITS

effects

1.10

iveness

1.07

 effects

0.87

 thereof

0.84

 havoc

0.83

Effects

0.82

bringer

0.82

Effect

0.80

ktop

0.78

ively

0.72

Activations Density 0.020%

terms related to the potential negative impacts or consequences of a medical treatment or substance

mentions of side effects and their severity

No Comments

No Known Activations