INDEX

Explanations

addresses or locations

oai_token-act-pair · gpt-3.5-turbo

numerical values or statistics

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

querque

-0.74

 newsp

-0.74

 loser

-0.70

 stuffing

-0.69

 quasi

-0.68

 federation

-0.66

 reluct

-0.64

itutes

-0.64

 sluggish

-0.64

 stacking

-0.64

POSITIVE LOGITS

 ILCS

1.38

1.03

1.01

0.97

0.96

0.92

çĶ°

0.92

Activations Density 0.084%

addresses or locations

numerical values or statistics

No Comments

No Known Activations