INDEX

Explanations

times and time zones in text

oai_token-act-pair · gpt-3.5-turbo

timestamps and event-related information

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

vim

-0.81

backer

-0.79

respond

-0.79

cer

-0.77

shr

-0.77

cci

-0.77

hm

-0.76

escal

-0.75

mean

-0.75

Wan

-0.74

POSITIVE LOGITS

EST

1.16

IFIED

1.13

LY

1.07

FUL

1.06

FORM

1.00

ITY

1.00

ORY

0.99

WOR

0.97

REAM

0.97

IM

0.96

Activations Density 0.029%

times and time zones in text

timestamps and event-related information

No Comments

No Known Activations