INDEX

Explanations

time references such as specific hours, minutes, and dates

oai_token-act-pair · gpt-3.5-turbo

time-related information and timings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 incorpor

-0.68

verages

-0.67

 Baton

-0.65

 Tucson

-0.65

comb

-0.64

Columb

-0.63

 helicop

-0.63

 spons

-0.62

 psychiat

-0.61

FontSize

-0.61

POSITIVE LOGITS

Dialogue

0.80

 Dialogue

0.77

<@

0.75

ropy

0.74

_>

0.73

SAY

0.71

<+

0.70

anian

0.68

ools

0.67

EMOTE

0.67

Activations Density 0.060%

time references such as specific hours, minutes, and dates

time-related information and timings

No Comments

No Known Activations