INDEX

Explanations

words related to verticality or directions like up and down

oai_token-act-pair · gpt-3.5-turbo

references to vertical alignment or orientation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

keeper

-0.91

giving

-0.88

keeping

-0.86

REDACTED

-0.84

keepers

-0.83

unes

-0.77

ptives

-0.75

ãģ¦

-0.75

mberg

-0.75

[&

-0.74

POSITIVE LOGITS

 axis

0.97

 dimension

0.94

 stabil

0.90

 ascent

0.90

 dimensions

0.86

 takeoff

0.85

 velocity

0.85

 vertical

0.85

 integration

0.85

 stripes

0.83

Activations Density 0.020%

words related to verticality or directions like up and down

references to vertical alignment or orientation

No Comments

No Known Activations