INDEX

Explanations

concepts related to obstacles or restrictions

oai_token-act-pair · gpt-3.5-turbo

references to obstacles or impediments in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

phis

-0.85

ivery

-0.84

ergy

-0.73

ories

-0.73

sch

-0.73

iability

-0.71

lihood

-0.70

ammad

-0.70

ribution

-0.69

doms

-0.68

POSITIVE LOGITS

 barriers

1.17

 barrier

1.03

 erected

1.00

 walls

0.92

 separating

0.90

buster

0.85

 Walls

0.81

 wall

0.79

 crossings

0.79

 Barrier

0.76

Activations Density 0.017%

concepts related to obstacles or restrictions

references to obstacles or impediments in various contexts

No Comments

No Known Activations