INDEX

Explanations

phrases related to rules, guidelines, or procedures

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate guidelines, recommendations, or strategies

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

edin

-0.84

nick

-0.82

beat

-0.74

athan

-0.72

flies

-0.66

Hug

-0.66

deen

-0.64

rax

-0.64

clair

-0.64

Champ

-0.64

POSITIVE LOGITS

 determining

1.24

 constructing

1.18

 resolving

1.17

 navigating

1.16

bidden

1.14

 interpreting

1.12

 implementing

1.09

 assessing

1.09

 evaluating

1.09

 accessing

1.08

Activations Density 0.170%

phrases related to rules, guidelines, or procedures

phrases that indicate guidelines, recommendations, or strategies

No Comments

No Known Activations