INDEX

Explanations

adjectives used to describe different levels of emphasis or importance

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "any" and related terms suggesting generality or inclusivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

rex

-0.87

expensive

-0.80

gypt

-0.69

efficient

-0.69

ovy

-0.66

raid

-0.65

staking

-0.65

ride

-0.65

romy

-0.65

arettes

-0.65

POSITIVE LOGITS

THING

1.13

 semblance

1.10

 conceivable

1.02

body

0.93

WHERE

0.91

 resemblance

0.89

 lingering

0.88

where

0.86

 possible

0.86

 attempt

0.85

Activations Density 0.067%

adjectives used to describe different levels of emphasis or importance

occurrences of the word "any" and related terms suggesting generality or inclusivity

No Comments

No Known Activations