INDEX

Explanations

names or places containing the letters "res"

oai_token-act-pair · gpt-3.5-turbo

references to specific places or venues

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

 Qing

-0.60

 caucuses

-0.60

VERTISEMENT

-0.60

glers

-0.60

\\\\\\\\\\\\\\\\

-0.60

doms

-0.58

 strings

-0.57

"{

-0.57

 Wilhelm

-0.56

 pound

-0.56

POSITIVE LOGITS

istance

1.29

idency

1.24

cue

1.22

olutions

1.08

erve

1.06

pring

1.06

idence

1.05

urrection

1.03

idents

1.02

cale

1.01

Activations Density 0.016%

names or places containing the letters "res"

references to specific places or venues

No Comments

No Known Activations