INDEX

Explanations

names, titles, and descriptions of research authors

oai_token-act-pair · gpt-3.5-turbo

references to academic titles and roles in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 voic

-0.77

 tape

-0.75

 revol

-0.74

 rails

-0.72

store

-0.72

 railing

-0.71

 revolt

-0.68

 ghetto

-0.67

 cringe

-0.67

 lockout

-0.66

POSITIVE LOGITS

 researcher

1.04

 neuroscience

1.03

 computational

1.02

 laboratory

1.02

 biomedical

1.01

 Laboratory

1.00

 microbi

0.99

 Neuroscience

0.96

 doctoral

0.96

 laboratories

0.94

Activations Density 0.408%

names, titles, and descriptions of research authors

references to academic titles and roles in research

No Comments

No Known Activations