INDEX

Explanations

dates in the format of years

oai_token-act-pair · gpt-3.5-turbo

years and specific dates related to events

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

gib

-0.75

tv

-0.64

dyn

-0.64

HH

-0.62

natureconservancy

-0.62

ksh

-0.61

JP

-0.61

 jelly

-0.60

 VIDEOS

-0.60

SPA

-0.59

POSITIVE LOGITS

furt

1.00

-'

0.95

etsk

0.73

abi

0.72

iannopoulos

0.71

arten

0.69

attering

0.69

 alleging

0.67

 onwards

0.67

oug

0.66

Activations Density 0.258%

dates in the format of years

years and specific dates related to events

No Comments

No Known Activations