INDEX

Explanations

dates expressed in two-digit numbers

oai_token-act-pair · gpt-3.5-turbo

historical dates and significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

malink

-0.63

 darn

-0.62

pse

-0.62

spin

-0.61

ep

-0.60

venge

-0.60

ancial

-0.60

 lineback

-0.59

 listener

-0.58

 masc

-0.58

POSITIVE LOGITS

GMT

0.92

-'

0.82

 onwards

0.79

BCE

0.78

GMT

0.77

sburg

0.75

æŃ¦

0.75

âĢ²

0.75

çļ

0.74

 Thames

0.70

Activations Density 0.055%

dates expressed in two-digit numbers

historical dates and significant events

No Comments

No Known Activations