INDEX

Explanations

words related to restrictive or controversial language

oai_token-act-pair · gpt-3.5-turbo

instances of the word "language" in various contexts, particularly concerning restrictions or implications surrounding it

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilon

-1.00

iary

-0.92

iaries

-0.88

rodu

-0.84

oppable

-0.83

kus

-0.83

romeda

-0.82

roxy

-0.81

arios

-0.80

erenn

-0.79

POSITIVE LOGITS

 spoken

1.08

 learners

1.02

language

0.96

 interpreter

0.92

 barrier

0.88

 language

0.88

anguage

0.85

 barriers

0.83

 comprehension

0.81

 deaf

0.79

Activations Density 0.021%

words related to restrictive or controversial language

instances of the word "language" in various contexts, particularly concerning restrictions or implications surrounding it

No Comments

No Known Activations