INDEX

Explanations

phrases related to medical conditions or health issues, specifically focusing on individuals with pre-existing conditions

oai_token-act-pair · gpt-3.5-turbo

references to people with specific conditions or characteristics

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

waters

-0.63

-0.62

press

-0.60

:-)

-0.59

fig

-0.59

uzz

-0.59

println

-0.59

review

-0.58

Fed

-0.58

obi

-0.58

POSITIVE LOGITS

stood

1.60

drawn

1.14

 disabilities

1.13

 regard

1.12

 whom

1.11

standing

1.10

 regards

1.05

 impunity

1.02

holding

1.00

 respect

0.98

Activations Density 0.096%

phrases related to medical conditions or health issues, specifically focusing on individuals with pre-existing conditions

references to people with specific conditions or characteristics

No Comments

No Known Activations