INDEX

Explanations

responses or reactions to various topics or situations

oai_token-act-pair · gpt-3.5-turbo

variations of the word "respond" and associated terms related to response or accountability

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

BALL

-0.81

fare

-0.74

ctors

-0.69

 devils

-0.69

âĸ¬

-0.66

âĢ¢âĢ¢

-0.64

 Tanzania

-0.63

WARE

-0.63

 Leone

-0.63

 Wand

-0.63

POSITIVE LOGITS

onding

1.09

awn

1.06

ibilities

0.99

onds

0.97

onder

0.97

rha

0.95

Resp

0.93

umph

0.92

ibly

0.92

ensible

0.91

Activations Density 0.019%

responses or reactions to various topics or situations

variations of the word "respond" and associated terms related to response or accountability

No Comments

No Known Activations