INDEX

Explanations

terms related to immunology, such as immunotherapy and immunization

oai_token-act-pair · gpt-3.5-turbo

terms related to immunology and immunotherapy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Camel

-0.70

 Dare

-0.69

 Pound

-0.69

 Witches

-0.68

HEAD

-0.67

 Carlton

-0.67

 halfway

-0.67

 Shelby

-0.66

 Dominion

-0.66

LER

-0.66

POSITIVE LOGITS

ities

1.35

ologically

1.16

ological

1.13

otherapy

1.11

isations

1.11

ogl

1.10

ologic

1.10

itÃ©

1.09

icip

1.07

ization

1.06

Activations Density 0.027%

terms related to immunology, such as immunotherapy and immunization

terms related to immunology and immunotherapy

No Comments

No Known Activations