INDEX

Explanations

specific mentions of time

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter "p" in various contexts, particularly in time references

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

 Halls

-0.71

 Orche

-0.69

FUL

-0.65

 Shining

-0.64

CVE

-0.64

æ©Ł

-0.63

ãĤ°

-0.63

OME

-0.63

eer

-0.62

 Eagle

-0.62

POSITIVE LOGITS

airs

1.08

orters

1.00

aired

0.97

okes

0.97

icks

0.91

ierce

0.91

ips

0.91

uffed

0.90

elt

0.90

enny

0.89

Activations Density 0.016%

specific mentions of time

occurrences of the letter "p" in various contexts, particularly in time references

No Comments

No Known Activations