INDEX

Explanations

words or prefixes related to negation or reversing actions

oai_token-act-pair · gpt-3.5-turbo

words that indicate a lack or negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

OPLE

-1.04

hetti

-0.82

 Dynamics

-0.81

jriwal

-0.79

anwhile

-0.78

ORY

-0.75

utical

-0.74

ãĥ¼ãĥĨãĤ£

-0.74

ħĭ

-0.72

uyomi

-0.71

POSITIVE LOGITS

balanced

1.15

cles

1.10

confirmed

1.10

apolog

1.10

ifying

1.09

assuming

1.09

classified

1.05

leased

1.05

rep

1.03

ruly

1.02

Activations Density 0.027%

words or prefixes related to negation or reversing actions

words that indicate a lack or negation

No Comments

No Known Activations