INDEX

Explanations

obstacles or hindrances within different contexts or scenarios

oai_token-act-pair · gpt-3.5-turbo

concepts related to challenges or hindrances

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

orp

-0.85

akening

-0.79

ulet

-0.78

orks

-0.77

daq

-0.75

elt

-0.72

overe

-0.71

ammad

-0.71

otide

-0.70

psc

-0.68

POSITIVE LOGITS

 obstacle

1.10

 obstacles

1.02

 hurdles

0.94

 imped

0.90

 barriers

0.88

 impede

0.81

 facing

0.81

 hurdle

0.78

 insur

0.73

 plag

0.73

Activations Density 0.029%

obstacles or hindrances within different contexts or scenarios

concepts related to challenges or hindrances

No Comments

No Known Activations